{"data":[{"id":"kilo-auto\/efficient","name":"Auto Efficient","created":0,"description":"Routes each request to the cheapest model that gets the job done, based on continuously benchmarked accuracy and cost.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"-1","completion":"-1","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"opencode":{},"inference_provider_ids":[],"preferredIndex":0,"isFree":false,"mayTrainOnYourPrompts":false,"autoRouting":{"models":["anthropic\/claude-haiku-5.5","deepseek\/deepseek-v4.1-flash-1017","google\/gemini-3.8-flash","inclusionai\/ling-3.1-flash","mistralai\/mistral-large-4-0","moonshotai\/kimi-k3","openai\/gpt-6-luna","qwen\/qwen3.8-flash","qwen\/qwen3.8-max-0902","stepfun\/step-5-preview","x-ai\/grok-4.7","xiaomi\/mimo-v2.6-pro","z-ai\/glm-5.3","z-ai\/glm-5.3-flash"]}},{"id":"kilo-auto\/free","name":"Auto Free","created":0,"description":"Rotates through available free models. Limited capability and no credits required. [Learn more](https:\/\/kilo.ai\/docs\/code-with-ai\/agents\/auto-model)\n\n**Warning** Prompts may be logged by the upstream provider and used to improve their services. Not suitable for production or sensitive data workloads.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":32768},"pricing":{"prompt":"0","completion":"0","input_cache_read":"0","input_cache_write":"0","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"context_length":256000,"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"opencode":{},"inference_provider_ids":[],"preferredIndex":1,"isFree":true,"mayTrainOnYourPrompts":true,"autoRouting":{"models":["baidu\/ernie-5.5-flash-preview:free","dots-studio\/dots-3-note-preview:free","nvidia\/nemotron-3-ultra-550b-a55b:free","nvidia\/nemotron-3.5-super-vl:free","stealth\/glyph-cluster"]}},{"id":"nvidia\/nemotron-3.5-super-vl:free","name":"NVIDIA: Nemotron 3.5 Super VL (free)","created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...\n\n**Terms of service** For NVIDIA free endpoints (Super\/Ultra\/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https:\/\/www.nvidia.com\/en-us\/about-nvidia\/privacy-policy\/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https:\/\/assets.ngc.nvidia.com\/products\/api-catalog\/legal\/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["nvidia"],"preferredIndex":2,"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"stealth\/glyph-cluster","name":"Glyph Cluster","created":1791331200,"description":"Glyph Cluster is an anonymous reasoning model in early access. Prompts and outputs will be retained by the provider.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":256000},"pricing":{"prompt":"0","completion":"0"},"context_length":256000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["stealth"],"preferredIndex":3,"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"anthropic\/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000002","input_cache_write":"0.000005","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"preferredIndex":4,"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"preferredIndex":5,"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"deepseek\/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":393216},"pricing":{"prompt":"0.000000300000","completion":"0.000001200000","input_cache_read":"0.000000006000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","deepinfra","deepseek","dekallm","digitalocean","fireworks","gmicloud","inference-net","ionstream","makora","mistral","modal","morph","near-ai","nebius","novita","open-inference","parasail","pareto","particle-ai","primalabs","primeintellect","reka","relace","river","runinfra","runware","sail-research","siliconflow","stepfun","streamlake","subconscious","telnyx","together","venice","wafer"],"preferredIndex":6,"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"z-ai\/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["atlas-cloud","baseten","boundless","cohere","coreweave","crusoe","darkbloom","deepinfra","dekallm","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","kt","makora","mistral","modal","morph","near-ai","nebius","nextbit","novita","open-inference","parasail","pareto","particle-ai","reka","relace","river","runinfra","runware","sail-research","siliconflow","streamlake","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"preferredIndex":7,"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"inclusionai\/ling-3.2-flash:free","name":"inclusionAI: Ling 3.2 Flash (free)","created":1794591958,"description":"Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":262144},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["antdigital"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-4-hydrogen","name":"Google: Gemini 4 Hydrogen","created":1794506460,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075","input_cache_read":"0.0000000375","input_cache_write":"0.0000000416666666666667","web_search":"0.014","internal_reasoning":"0.00000375","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"baidu\/ernie-5.5-flash-preview:free","name":"Baidu: ERNIE-5.5-Flash-Preview (free)","created":1794333533,"description":"ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1024000,"max_completion_tokens":921600},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":1024000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["baidu"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["high"]}]}},{"id":"baidu\/ernie-light-dt-1.0-intl","name":"Baidu: ERNIE-Light-DT-1.0","created":1794331260,"description":"ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1024000,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000113","completion":"0.00000394","input_cache_read":"0.000000113","discount":0},"context_length":1024000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["baidu"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"google\/gemini-4-carbon","name":"Google: Gemini 4 Carbon","created":1794326871,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000002000000","completion":"0.000010000000","image":"0.000002000000","input_cache_read":"0.000000100000","input_cache_write":"0.000000187500","web_search":"0.028000000000","internal_reasoning":"0.000010000000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"nex-agi\/nex-n2.6","name":"Nex AGI: Nex-N2.6","created":1794282379,"description":"Nex-N2.6 is an agentic model from Nex AGI, built on [GLM-5.3-Flash](https:\/\/huggingface.co\/zai-org\/GLM-5.3-Flash-BF16) with about 321B parameters. It is suited for computer use, coding, and long-horizon tasks that involve tools. Compared with...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.000000150000","completion":"0.000000500000","input_cache_read":"0.000000030000"},"context_length":262144,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["medium","high"]}]}},{"id":"thinkingmachines\/inkling-2-small","name":"Thinking Machines: Inkling 2 Small","created":1794261847,"description":"Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["cloudflare","deepinfra","modal","nebius","primeintellect","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","max"]}]}},{"id":"anthropic\/claude-fable-5.2","name":"Anthropic: Claude Fable 5.2","created":1794253781,"description":"Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000008","completion":"0.00004","input_cache_read":"0.0000002","input_cache_write":"0.00001","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"meta\/muse-ember","name":"Meta: Muse Ember","created":1794247648,"description":"Muse Ember is the smallest and most efficient model from Meta that\u2019s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.000000004","web_search":"0.01","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","meta"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}]}},{"id":"liquid\/lfm-3-1.7b","name":"LiquidAI: LFM3-1.7B","created":1794009477,"description":"A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000008","completion":"0.0000002","input_cache_read":"0.00000002","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["liquid"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"liquid\/lfm-3-1.7b:free","name":"LiquidAI: LFM3-1.7B (free)","created":1794009477,"description":"A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":8192},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["liquid"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"google\/gemini-omni-1.2-flash","name":"Google: Gemini Omni 1.2 Flash","created":1793898961,"description":"Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...","architecture":{"modality":"text+image+video->text+video","input_modalities":["text","image","video","pdf"],"output_modalities":["text","video"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":65536},"pricing":{"prompt":"0.0000015","completion":"0.000009","web_search":"0.014","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","high"]}]}},{"id":"kt\/midm-k-3.0-pro","name":"KT: Mi:dm K 3.0 Pro","created":1793897701,"description":"Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":261795,"max_completion_tokens":235615},"pricing":{"prompt":"0.0000002","completion":"0.0000008","input_cache_read":"0.00000004","discount":0},"context_length":261795,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["kt"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-omni-1.1-flash","name":"Google: Gemini Omni 1.1 Flash","created":1793825668,"description":"Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and...","architecture":{"modality":"text+image+video->text+video","input_modalities":["text","image","video","pdf"],"output_modalities":["text","video"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":65536},"pricing":{"prompt":"0.0000015","completion":"0.000009","web_search":"0.014","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","high"]}]}},{"id":"ricursiveai\/ripple-65b-preview","name":"Ricursive: Ripple 65B Preview","created":1793818990,"description":"Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000001","completion":"0.0000003","input_cache_read":"0.000000025","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["gmicloud","primeintellect","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"tencent\/hy4","name":"Tencent: Hy4","created":1793766031,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000834000","completion":"0.000002501000","input_cache_read":"0.000000042000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"expiration_date":null,"inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","low","high"]}]}},{"id":"motif-technologies\/motif-3","name":"Motif Technologies: Motif 3","created":1793655334,"description":"Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters. It is a general-purpose multilingual model for English and Korean, particularly strong at...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["kt"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"z-ai\/glm-5.3-flashx-legal","name":"Z.ai: GLM 5.3 FlashX Legal","created":1793626154,"description":"GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000037","completion":"0.00000125","input_cache_read":"0.000000075"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"particle-ai\/particle-1","name":"Particle AI: Particle-1","created":1793207893,"description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000006","completion":"0.0000005","input_cache_read":"0.000000003","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["particle-ai"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}]}},{"id":"particle-ai\/particle-1:free","name":"Particle AI: Particle-1 (free)","created":1793207893,"description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["particle-ai"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6.1-terra-pro","name":"OpenAI: GPT-6.1 Terra Pro","created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https:\/\/openrouter.ai\/openai\/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.00000125","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6.1-terra","name":"OpenAI: GPT-6.1 Terra","created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.00000125","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"moonshotai\/kimi-k3.1-pro","name":"MoonshotAI: Kimi K3.1 Pro","created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000002403","completion":"0.0000084023","input_cache_read":"0.0000002"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","alibaba","baseten","boundless","decart","deepinfra","digitalocean","fireworks","inference-net","modal","moonshotai","morph","nebius","parasail","pareto","primalabs","relace","river","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"minimax\/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","created":1792379569,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":524288},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["digitalocean","fireworks","gmicloud","inferact-vllm","inference-net","minimax","nebius","novita","parasail","sambanova","streamlake","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"elorian\/glimpse","name":"Elorian: Glimpse","created":1792206629,"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":256000},"pricing":{"prompt":"0.0000006","completion":"0.000003","input_cache_read":"0.00000006","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["elorian","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"reflection\/beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","created":1792160499,"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.00000025","completion":"0.000001","input_cache_read":"0.00000005","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["baseten","coreweave","digitalocean","nebius","reflection","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"prism-ml\/ternary-bonsai-2-9b","name":"PrismML: Ternary Bonsai 2 9B","created":1792130995,"description":"Ternary Bonsai 2 9B is PrismML\u2019s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000008","completion":"0.00000013","input_cache_read":"0.00000004","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["darkbloom"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"moondream\/moondream3-preview","name":"Moondream: Moondream 3 Preview","created":1792102385,"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":32000,"max_completion_tokens":4096},"pricing":{"prompt":"0.0000003","completion":"0.0000025","discount":0},"context_length":32000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["primeintellect"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"moondream\/moondream3.1-9b-a2b","name":"Moondream: Moondream 3.1","created":1792102373,"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":32000,"max_completion_tokens":4096},"pricing":{"prompt":"0.0000003","completion":"0.0000025","discount":0},"context_length":32000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["primeintellect"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"meta\/muse-spark-open","name":"Meta: Muse Spark Open","created":1792087069,"description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.00000125","completion":"0.00000425","input_cache_read":"0.00000015","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["baseten","fireworks","modal","nebius","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"nvidia\/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.00000006","completion":"0.00000035","input_cache_read":"0.00000001","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["baseten","coreweave","crusoe","darkbloom","deepinfra","io-net","nebius","primeintellect","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"unbiased\/pareto-26.10","name":"Pareto 26.10","created":1792073620,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000008","completion":"0.0000032","input_cache_read":"0.00000003","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"alias_target":"unbiased\/pareto-26.10","id":"~unbiased\/pareto-latest","name":"Pareto Latest","created":1791933050,"description":"This model always redirects to the latest model in the Pareto family.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000008","completion":"0.0000032","input_cache_read":"0.00000003"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"unbiased\/pareto-26.9","name":"Pareto 26.9","created":1791930537,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000025","completion":"0.0000075","input_cache_read":"0.00000025","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["max_tokens","response_format","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"liquid\/lfm-2.5-24b-a2b","name":"LiquidAI: LFM2.5-24B-A2B","created":1791912025,"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000005","completion":"0.0000007","input_cache_read":"0.000000025","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["liquid"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"google\/gemini-4-argon","name":"Google: Gemini 4 Argon","created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000002000000","completion":"0.000010000000","image":"0.000002000000","input_cache_read":"0.000000100000","input_cache_write":"0.000000187500","web_search":"0.028000000000","internal_reasoning":"0.000010000000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"scaledown\/summarize","name":"ScaleDown: Summarize","created":1791893360,"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":4000},"pricing":{"prompt":"0.000000050000","completion":"0.000000000000"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["max_tokens"],"expiration_date":null,"inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"scaledown\/extract","name":"ScaleDown: Extract","created":1791893351,"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":900000},"pricing":{"prompt":"0.000000050000","completion":"0.000000000000"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["max_tokens"],"expiration_date":null,"inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"meta\/muse-wonder","name":"Meta: Muse Wonder","created":1791807945,"description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000002","web_search":"0.01","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","meta"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}]}},{"id":"stepfun\/step-5-preview","name":"StepFun: Step 5 Preview","created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active \/ 600B total parameters). It performs strongly in software engineering and professional...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":64000},"pricing":{"prompt":"0.000001","completion":"0.0000027","input_cache_read":"0.0000001","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["featherless","stepfun","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"anthropic\/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"google\/gemini-nano-banana-2.1","name":"Google: Nano Banana 2.1","created":1791300825,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","architecture":{"modality":"text+image->text+image","input_modalities":["image","text","pdf"],"output_modalities":["image","text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":58982},"pricing":{"prompt":"0.0000015","completion":"0.0000075","web_search":"0.014","discount":0},"context_length":65536,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}]}},{"id":"mistralai\/mistral-large-4-0","name":"Mistral: Mistral Large 4","created":1791294122,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":262144},"pricing":{"prompt":"0.0000007","completion":"0.0000021","input_cache_read":"0.00000007","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","high"]}]}},{"id":"inclusionai\/ling-3.1-flash","name":"inclusionAI: Ling 3.1 Flash","created":1790950024,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":262144},"pricing":{"prompt":"0.000000300000","completion":"0.000000900000","input_cache_read":"0.000000060000"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"unbiased\/pareto-26.10-preview","name":"Pareto 26.10 Preview","created":1790863623,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000008","completion":"0.0000032","input_cache_read":"0.00000003","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["max_tokens","response_format","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https:\/\/openrouter.ai\/openai\/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"anthropic\/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"perceptron\/perceptron-mk1.5","name":"Perceptron: Perceptron Mk1.5","created":1790352661,"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":36864,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000015","completion":"0.0000015","discount":0},"context_length":36864,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["perceptron"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}]}},{"id":"fireworks\/ember-1","name":"Fireworks: Ember-1","created":1790208461,"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https:\/\/openrouter.ai\/moonshotai\/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["fireworks"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"z-ai\/glm-5.3-prime","name":"Z.ai: GLM 5.3 Prime","created":1790199651,"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5\u20132\u00d7 the output throughput through inference acceleration. It supports text input and output with a 1M-token...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000028","completion":"0.0000088","input_cache_read":"0.00000056"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"qwen\/qwen3.8-max-prime","name":"Qwen: Qwen3.8 Max Prime","created":1790191228,"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.000004","completion":"0.000012","input_cache_read":"0.0000005","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}]}},{"id":"aion-labs\/aion-3.5-mini","name":"AionLabs: Aion 3.5 Mini","created":1790170962,"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000007","completion":"0.0000014","input_cache_read":"0.00000018","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"aion-labs\/aion-3.5","name":"AionLabs: Aion 3.5","created":1790170961,"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":32768},"pricing":{"prompt":"0.000003","completion":"0.000006","input_cache_read":"0.00000075","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"upstage\/solar-mini4","name":"Upstage: Solar Mini 4","created":1790160358,"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":524288,"max_completion_tokens":131072},"pricing":{"prompt":"0.000000100000","completion":"0.000000400000","input_cache_read":"0.000000010000"},"context_length":524288,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}]}},{"id":"cohere\/command-a-plus","name":"Cohere: Command A+","created":1790102896,"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Cohere"},"top_provider":{"is_moderated":true,"context_length":192000,"max_completion_tokens":64000},"pricing":{"prompt":"0.0000003","completion":"0.0000015","input_cache_read":"0.00000015","discount":0},"context_length":192000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https:\/\/openrouter.ai\/openai\/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6-luna","name":"OpenAI: GPT-6 Luna","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https:\/\/openrouter.ai\/openai\/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6-sol","name":"OpenAI: GPT-6 Sol","created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"xiaomi\/mimo-v2.6-pro-ultraspeed","name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","created":1790021267,"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000435","completion":"0.0000087","input_cache_read":"0.000000036","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"xiaomi\/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000001","completion":"0.00000028","input_cache_read":"0.0000000028","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["boundless","cohere","darkbloom","deepinfra","gmicloud","inference-net","makora","novita","tencent","tenstorrent","venice","xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"xiaomi\/mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","created":1790021259,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.000000435000","completion":"0.000000870000","input_cache_read":"0.000000004000"},"context_length":1050000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["boundless","deepinfra","gmicloud","novita","primalabs","streamlake","tencent","xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"x-ai\/grok-4.7","name":"SpaceXAI: Grok 4.7","created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Grok"},"top_provider":{"is_moderated":false,"context_length":500000,"max_completion_tokens":450000},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000005","input_cache_write":"0","web_search":"0.01","discount":0},"context_length":500000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"qwen\/qwen3.8-omni-flash","name":"Qwen: Qwen3.8 Omni Flash","created":1789959954,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","audio","video"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000015","completion":"0.00000047","input_cache_read":"0.000000016","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"prism-ml\/ternary-bonsai-2-27b","name":"PrismML: Ternary Bonsai 2 27B","created":1789754046,"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":32768},"pricing":{"prompt":"0.000000075","completion":"0.0000005","input_cache_read":"0.0000000375","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["darkbloom"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","medium","xhigh"]}]}},{"id":"z-ai\/glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","created":1789744020,"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens\/s. Built on the same hybrid sparse and linear attention architecture...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000037","completion":"0.00000125","input_cache_read":"0.000000075"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"alias_target":"deepseek\/deepseek-v4-pro-0813","id":"~deepseek\/deepseek-pro-latest","name":"DeepSeek: DeepSeek Pro Latest","created":1789399174,"description":"This model always redirects to the latest model in the DeepSeek Pro family.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":393216},"pricing":{"prompt":"0.0000000999","completion":"0.000008","input_cache_read":"0.0000000999"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","deepseek","digitalocean","gmicloud","nebius","novita","parasail","relace","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"alias_target":"deepseek\/deepseek-v4.1-flash-1017","id":"~deepseek\/deepseek-flash-latest","name":"DeepSeek: DeepSeek Flash Latest","created":1789399150,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":384000},"pricing":{"prompt":"0.00000002","completion":"0.000000108","input_cache_read":"0.000000007"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","deepinfra","deepseek","dekallm","digitalocean","fireworks","gmicloud","inference-net","ionstream","makora","mistral","modal","morph","near-ai","nebius","novita","open-inference","parasail","pareto","particle-ai","primalabs","primeintellect","reka","relace","river","runinfra","runware","sail-research","siliconflow","stepfun","streamlake","subconscious","telnyx","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"inference-net\/schematron-v2-turbo","name":"Inference.net: Schematron V2 Turbo","created":1789176949,"description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000003","completion":"0.00000015","input_cache_read":"0.00000003","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["inference-net"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"inference-net\/schematron-v2-small","name":"Inference.net: Schematron V2 Small","created":1789176933,"description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000005","completion":"0.00000023","input_cache_read":"0.00000005","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["inference-net"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"alias_target":"openai\/gpt-6-astra","id":"~openai\/gpt-astra-latest","name":"OpenAI: GPT Astra Latest ($$$$)","created":1789130932,"description":"This model always redirects to the latest model in the GPT Astra family.","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","web_search":"0.01"},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"alias_target":"openai\/gpt-6.1-sol","id":"~openai\/gpt-sol-latest","name":"OpenAI: GPT Sol Latest","created":1789130928,"description":"This model always redirects to the latest model in the GPT Sol family.","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","web_search":"0.01"},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"alias_target":"openai\/gpt-6.1-terra","id":"~openai\/gpt-terra-latest","name":"OpenAI: GPT Terra Latest","created":1789130925,"description":"This model always redirects to the latest model in the GPT Terra family.","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.00000125","web_search":"0.01"},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"alias_target":"openai\/gpt-6-luna","id":"~openai\/gpt-luna-latest","name":"OpenAI: GPT Luna Latest","created":1789130922,"description":"This model always redirects to the latest model in the GPT Luna family.","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01"},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"sakana\/fugu-ultra-v2","name":"Sakana: Fugu Ultra v2","created":1789105383,"description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"expiration_date":null,"inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}]}},{"id":"sakana\/fugu-max","name":"Sakana: Fugu Max","created":1789104771,"description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"expiration_date":null,"inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}]}},{"id":"inclusionai\/ling-3.0-flash-vl","name":"inclusionAI: Ling 3.0 Flash VL","created":1789056114,"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total \/ 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":32768},"pricing":{"prompt":"0.00000006","completion":"0.00000018","input_cache_read":"0.000000012","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"deepseek\/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":393216},"pricing":{"prompt":"0.000000300000","completion":"0.000001200000","input_cache_read":"0.000000006000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.75280899,"avgAttemptCostUsd":2.5831196000000003},"inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cohere","coreweave","crusoe","deepinfra","deepseek","digitalocean","fireworks","gmicloud","google-vertex","inference-net","makora","mancer","modal","morph","novita","open-inference","parasail","pareto","particle-ai","reka","relace","river","runinfra","runware","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"nex-agi\/nex-n2.5-mini","name":"Nex AGI: Nex-N2.5-Mini","created":1788890061,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.000000025","completion":"0.0000001","input_cache_read":"0.0000000025","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}]}},{"id":"nex-agi\/nex-n2.5-pro","name":"Nex AGI: Nex-N2.5-Pro","created":1788890050,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.000000075","completion":"0.00000025","input_cache_read":"0.000000015","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}]}},{"id":"openai\/gpt-6-astra","name":"OpenAI: GPT-6 Astra ($$$$)","created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.79325843,"avgAttemptCostUsd":107.293192},"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro ($$$$)","created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https:\/\/openrouter.ai\/openai\/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"qwen\/qwen3.8-max-0902","name":"Qwen: Qwen3.8 Max (0902)","created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","input_cache_write":"0.0000025","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}]}},{"id":"meta\/muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta\u2019s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.000000002","web_search":"0.0025","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}]}},{"id":"meta\/muse-spark-1.3","name":"Meta: Muse Spark 1.3","created":1788378359,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.00000125","completion":"0.00000425","input_cache_read":"0.00000015","web_search":"0.01","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","meta"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}]}},{"id":"google\/gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000750000","completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","web_search":"0.028000000000","internal_reasoning":"0.000003750000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.75280899,"avgAttemptCostUsd":112.2663174},"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"anthropic\/claude-fable-5.1","name":"Anthropic: Claude Fable 5.1 ($$$$)","created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.00000025","input_cache_write":"0.0000125","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.76179775,"avgAttemptCostUsd":91.4074256},"inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"ibm-granite\/granite-4.2-8b","name":"IBM: Granite 4.2 8B","created":1788206780,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":117964},"pricing":{"prompt":"0.00000006","completion":"0.00000015","input_cache_read":"0.000000015","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["coreweave","deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","low","high"]}]}},{"id":"tencent\/hy4-preview","name":"Tencent: Hy4 preview","created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":64000},"pricing":{"prompt":"0.000000834","completion":"0.000002501","input_cache_read":"0.000000042","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["atlas-cloud","deepinfra","gmicloud","novita","siliconflow","tencent","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","low","high"]}]}},{"alias_target":"z-ai\/glm-5.3-flash","id":"~z-ai\/glm-flash-latest","name":"Z.ai: GLM Flash Latest","created":1787817633,"description":"This model always redirects to the latest model in the GLM Flash family.","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000000399","completion":"0.0000000784","input_cache_read":"0.00000003"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["atlas-cloud","baseten","boundless","cohere","coreweave","crusoe","darkbloom","deepinfra","dekallm","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","kt","makora","mistral","modal","morph","near-ai","nebius","nextbit","novita","open-inference","parasail","pareto","particle-ai","reka","relace","river","runinfra","runware","sail-research","siliconflow","streamlake","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"qwen\/qwen3.8-flash","name":"Qwen: Qwen3.8 Flash","created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000015","completion":"0.00000047","input_cache_read":"0.000000016","input_cache_write":"0.0000002","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"meta\/muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","created":1787336476,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It\u2019s meaningfully cheaper than Muse Spark...","architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.000000002","web_search":"0.0025","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}]}},{"id":"deepseek\/deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https:\/\/openrouter.ai\/deepseek\/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":1048575,"max_completion_tokens":943717},"pricing":{"prompt":"0.00000044","completion":"0.00000132","input_cache_read":"0.000000014"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"tencent\/hy-mt2-1.8b","name":"Tencent: Hy-MT2-1.8B","created":1787231581,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":4096},"pricing":{"prompt":"0.000000044","completion":"0.000000177","discount":0},"context_length":8192,"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","stop","temperature"],"expiration_date":null,"inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"tencent\/hy-mt2-30b-a3b","name":"Tencent: Hy-MT2-30B-A3B","created":1787231561,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":4096},"pricing":{"prompt":"0.000000074","completion":"0.000000295","discount":0},"context_length":8192,"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"expiration_date":null,"inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"alias_target":"z-ai\/glm-5.3","id":"~z-ai\/glm-latest","name":"Z.ai: GLM Latest","created":1787151053,"description":"This model always redirects to the latest GLM model from Z.ai.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000000699","completion":"0.0000014","input_cache_read":"0.0000000689"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","alibaba","amazon-bedrock","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","decart","deepinfra","digitalocean","doubleword","featherless","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","morph","nebius","novita","parasail","reka","relace","runinfra","runware","sail-research","sambanova","siliconflow","streamlake","subconscious","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"tencent\/hy-mt2-7b","name":"Tencent: Hy-MT2-7B","created":1787148797,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":4096},"pricing":{"prompt":"0.000000074","completion":"0.000000295","discount":0},"context_length":8192,"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"expiration_date":null,"inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"z-ai\/glm-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000001400000","completion":"0.000004400000","input_cache_read":"0.000000260000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","alibaba","amazon-bedrock","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","decart","deepinfra","digitalocean","doubleword","featherless","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","morph","nebius","novita","parasail","reka","relace","runinfra","runware","sail-research","sambanova","siliconflow","streamlake","subconscious","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"qwen\/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.000000425","completion":"0.00000255","input_cache_read":"0.000000085","input_cache_write":"0.00000053125","discount":0},"context_length":1024000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","alibaba","cerebras","chutes","cloudflare","coreweave","darkbloom","deepinfra","dekallm","gmicloud","ionstream","mancer","modal","near-ai","nebius","novita","parasail","primeintellect","reka","runinfra","streamlake","tenstorrent","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}]}},{"id":"dots-studio\/dots-3-note-preview:free","name":"Dots Studio: Dots3-Note Preview (free)","created":1786680361,"description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":512000,"max_completion_tokens":460800},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":512000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":"2026-12-31","inference_provider_ids":["atlas-cloud"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-3.7-flash","name":"Google: Gemini 3.7 Flash","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000750000","completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","web_search":"0.028000000000","internal_reasoning":"0.000003750000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"bytedance-seed\/seed-2-1-turbo","name":"ByteDance Seed: Seed 2.1 Turbo","created":1786552176,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.0000005","completion":"0.0000025","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](\/qwen\/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","input_cache_write":"0.0000025","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","fireworks","gmicloud","modal","novita","siliconflow","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}]}},{"id":"deepseek\/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000001320000","completion":"0.000003960000","input_cache_read":"0.000000044000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","deepseek","digitalocean","gmicloud","nebius","novita","parasail","relace","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"x-ai\/grok-4.6","name":"SpaceXAI: Grok 4.6","created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](\/x-ai\/grok-4.7).","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Grok"},"top_provider":{"is_moderated":false,"context_length":500000,"max_completion_tokens":450000},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000005","web_search":"0.005","discount":0},"context_length":500000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.73033708,"avgAttemptCostUsd":33.829006},"inference_provider_ids":["amazon-bedrock","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]},"enkrypt":{"model_name":"grok-4.6","provider":"openai_compatible","source":"xAI","risk_score":12.683,"bias_score":35.14,"cbrn_score":24,"harmful_score":0.56,"insecure_code_score":0.44,"toxicity_score":3.27,"robustness_score":null,"jailbreak_score":7.33813,"evasion_score":null,"safety_score":19.9679,"nist_score":13,"owasp_score":14,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"nvidia\/nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.000000025","completion":"0.00000012","input_cache_read":"0.0000000125","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["coreweave","darkbloom","deepinfra","fireworks","runinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"nvidia\/nemotron-3.5-lightning:free","name":"NVIDIA: Nemotron 3.5 Lightning (free)","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...\n\n**Terms of service** For NVIDIA free endpoints (Super\/Ultra\/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https:\/\/www.nvidia.com\/en-us\/about-nvidia\/privacy-policy\/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https:\/\/assets.ngc.nvidia.com\/products\/api-catalog\/legal\/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"sakana\/sakana-namazu","name":"Sakana: Sakana Namazu","created":1786410129,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000095","completion":"0.000004","input_cache_read":"0.00000015","web_search":"0.007","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"expiration_date":null,"inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","high"]}]}},{"id":"upstage\/solar-pro4","name":"Upstage: Solar Pro 4","created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":524288,"max_completion_tokens":131072},"pricing":{"prompt":"0.000000300000","completion":"0.000001200000","input_cache_read":"0.000000060000"},"context_length":524288,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["kt","upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}]}},{"id":"meta\/muse-glimmer-30b","name":"Meta: Muse Glimmer 30B","created":1786302394,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","architecture":{"modality":"text+image->text","input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":16384},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000004","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"inclusionai\/ling-3.0-tiny","name":"inclusionAI: Ling 3.0 Tiny","created":1786034890,"description":"Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":250000},"pricing":{"prompt":"0.000000015","completion":"0.000000045","input_cache_read":"0.000000003","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["antdigital"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"meta\/muse-spark-1.2","name":"Meta: Muse Spark 1.2","created":1785959287,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.00000125","completion":"0.00000425","input_cache_read":"0.00000015","web_search":"0.0025","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.51460674,"avgAttemptCostUsd":44.68511},"inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}]}},{"alias_target":"deepseek\/deepseek-v4-flash-0731","id":"~deepseek\/deepseek-v4-flash-latest","name":"DeepSeek: DeepSeek V4 Flash Latest","created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000000434","completion":"0.0000003","input_cache_read":"0.000000035"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","chutes","cloudflare","cohere","coreweave","deepinfra","digitalocean","gmicloud","inceptron","mancer","morph","novita","parasail","primeintellect","reka","relace","runware","sail-research","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"deepseek\/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000000440000","completion":"0.000001320000","input_cache_read":"0.000000028000"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","chutes","cloudflare","cohere","coreweave","deepinfra","digitalocean","gmicloud","inceptron","mancer","morph","novita","parasail","primeintellect","reka","relace","runware","sail-research","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"thinkingmachines\/inkling-small","name":"Thinking Machines: Inkling Small","created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":524288,"max_completion_tokens":262144},"pricing":{"prompt":"0.00000045","completion":"0.0000012","input_cache_read":"0.0000001","discount":0},"context_length":524288,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","thinkingmachines"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}]}},{"id":"qwen\/qwen3.7-flash","name":"Qwen: Qwen3.7 Flash","created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000003","completion":"0.00000013","input_cache_read":"0.000000006","input_cache_write":"0.000000038","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"anthropic\/claude-opus-5","name":"Anthropic: Claude Opus 5","created":1784912544,"description":"Claude Opus 5 is Anthropic\u2019s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.71460674,"avgAttemptCostUsd":113.5366288},"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]},"enkrypt":{"model_name":"claude-opus-5","provider":"openai_compatible","source":"Anthropic","risk_score":13.8351,"bias_score":40.83,"cbrn_score":25.17,"harmful_score":0.56,"insecure_code_score":0.44,"toxicity_score":2.18,"robustness_score":null,"jailbreak_score":11.5108,"evasion_score":null,"safety_score":19.4868,"nist_score":14,"owasp_score":15,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"inclusionai\/ling-3.0-flash","name":"inclusionAI: Ling 3.0 Flash","created":1784818580,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":32768},"pricing":{"prompt":"0.000000060000","completion":"0.000000180000","input_cache_read":"0.000000012000"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","web_search":"0.014","internal_reasoning":"0.000001875","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.47865169,"avgAttemptCostUsd":80.3143008},"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]},"enkrypt":{"model_name":"gemini-3.6-flash","provider":"openai_compatible","source":"google","risk_score":35.5088,"bias_score":83.72,"cbrn_score":52.83,"harmful_score":8.89,"insecure_code_score":27.56,"toxicity_score":4.55,"robustness_score":null,"jailbreak_score":28.4892,"evasion_score":null,"safety_score":43.7851,"nist_score":36,"owasp_score":40,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"google\/gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","web_search":"0.014","internal_reasoning":"0.00000125","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]}},{"id":"meituan\/longcat-2.0","name":"Meituan: LongCat 2.0","created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048756,"max_completion_tokens":262144},"pricing":{"prompt":"0.000000750000","completion":"0.000003000000","input_cache_read":"0.000000015000"},"context_length":1048756,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["atlas-cloud"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"thinkingmachines\/inkling","name":"Thinking Machines: Inkling","created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":524288,"max_completion_tokens":471859},"pricing":{"prompt":"0.000001","completion":"0.00000405","input_cache_read":"0.00000017","discount":0},"context_length":524288,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.43595506,"avgAttemptCostUsd":35.689686},"inference_provider_ids":["modal","thinkingmachines","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}]},"enkrypt":{"model_name":"Inkling","provider":"together","source":"ThinkingMachines","risk_score":15.2186,"bias_score":60.98,"cbrn_score":8.67,"harmful_score":2.22,"insecure_code_score":2.22,"toxicity_score":2,"robustness_score":null,"jailbreak_score":0.719424,"evasion_score":null,"safety_score":24.2983,"nist_score":15,"owasp_score":19,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"moonshotai\/kimi-k3","name":"MoonshotAI: Kimi K3","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","input_cache_write":"0.00000375","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.72808989,"avgAttemptCostUsd":48.378817},"inference_provider_ids":["alibaba","amazon-bedrock","baseten","boundless","chutes","deepinfra","digitalocean","fireworks","inference-net","io-net","kt","makora","modal","moonshotai","morph","nebius","parasail","relace","river","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"meta\/muse-spark-1.1","name":"Meta: Muse Spark 1.1","created":1784215741,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....","architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.00000125","completion":"0.00000425","input_cache_read":"0.00000015","web_search":"0.0025","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.59775281,"avgAttemptCostUsd":30.153412199999998},"inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}]},"enkrypt":{"model_name":"muse-spark-1.1","provider":"openai_compatible","source":"Meta","risk_score":15.9875,"bias_score":50.13,"cbrn_score":6.33,"harmful_score":0,"insecure_code_score":19.11,"toxicity_score":4.36,"robustness_score":null,"jailbreak_score":1.43885,"evasion_score":null,"safety_score":23.1756,"nist_score":16,"owasp_score":20,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https:\/\/openrouter.ai\/openai\/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000002","completion":"0.0000012","input_cache_read":"0.00000002","input_cache_write":"0.00000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000002","completion":"0.0000012","input_cache_read":"0.00000002","input_cache_write":"0.00000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]},"enkrypt":{"model_name":"gpt-5.6-luna","provider":"openai","source":"openai","risk_score":22.8769,"bias_score":78.04,"cbrn_score":22.17,"harmful_score":0,"insecure_code_score":8,"toxicity_score":6.18,"robustness_score":null,"jailbreak_score":9.64029,"evasion_score":null,"safety_score":33.6808,"nist_score":23,"owasp_score":27,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https:\/\/openrouter.ai\/openai\/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]},"enkrypt":{"model_name":"gpt-5.6-terra","provider":"openai","source":"openai","risk_score":19.0053,"bias_score":60.72,"cbrn_score":20,"harmful_score":2.22,"insecure_code_score":4.44,"toxicity_score":7.64,"robustness_score":null,"jailbreak_score":8.48921,"evasion_score":null,"safety_score":28.2277,"nist_score":19,"owasp_score":22,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https:\/\/openrouter.ai\/openai\/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000004","input_cache_write":"0.000005","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000004","input_cache_write":"0.000005","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.76179775,"avgAttemptCostUsd":87.40998859999999},"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]},"enkrypt":{"model_name":"gpt-5.6-sol","provider":"openai","source":"openai","risk_score":21.5671,"bias_score":72.09,"cbrn_score":19.17,"harmful_score":0.56,"insecure_code_score":7.11,"toxicity_score":8.91,"robustness_score":null,"jailbreak_score":9.20863,"evasion_score":null,"safety_score":31.7562,"nist_score":22,"owasp_score":25,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"x-ai\/grok-4.5","name":"SpaceXAI: Grok 4.5","created":1783523154,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Grok"},"top_provider":{"is_moderated":false,"context_length":500000,"max_completion_tokens":450000},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000003","web_search":"0.005","discount":0},"context_length":500000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.70786517,"avgAttemptCostUsd":27.291154},"inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]},"enkrypt":{"model_name":"grok-4.5","provider":"openai_compatible","source":"xAI","risk_score":19.5645,"bias_score":66.41,"cbrn_score":25.33,"harmful_score":0,"insecure_code_score":0.44,"toxicity_score":5.64,"robustness_score":null,"jailbreak_score":10.3597,"evasion_score":null,"safety_score":29.591,"nist_score":20,"owasp_score":22,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"alias_target":"x-ai\/grok-4.7","id":"~x-ai\/grok-latest","name":"xAI: Grok Latest","created":1783519360,"description":"This model always redirects to the latest Grok model from xAI.","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":true,"context_length":500000,"max_completion_tokens":450000},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000005","input_cache_write":"0","web_search":"0.01"},"context_length":500000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"aion-labs\/aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","created":1783443096,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000007","completion":"0.0000014","input_cache_read":"0.00000018","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"aion-labs\/aion-3.0","name":"AionLabs: Aion-3.0","created":1783443095,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":32768},"pricing":{"prompt":"0.000003","completion":"0.000006","input_cache_read":"0.00000075","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"tencent\/hy3","name":"Tencent: Hy3","created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":128000},"pricing":{"prompt":"0.000000132","completion":"0.000000528","input_cache_read":"0.000000033","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["atlas-cloud","gmicloud","novita","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","low","high"]}]},"enkrypt":{"model_name":"hy3","provider":"novita","source":"tencent","risk_score":15.1549,"bias_score":56.07,"cbrn_score":0.5,"harmful_score":7.22,"insecure_code_score":8.89,"toxicity_score":3.09,"robustness_score":null,"jailbreak_score":1.8705,"evasion_score":null,"safety_score":20.6095,"nist_score":15,"owasp_score":19,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"anthropic\/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000002","input_cache_write":"0.0000025","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.59550562,"avgAttemptCostUsd":36.186279799999994},"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]},"enkrypt":{"model_name":"claude-sonnet-5","provider":"anthropic","source":"anthropic","risk_score":9.20561,"bias_score":29.46,"cbrn_score":7.5,"harmful_score":0,"insecure_code_score":8.89,"toxicity_score":0.18,"robustness_score":null,"jailbreak_score":2.01439,"evasion_score":null,"safety_score":13.3119,"nist_score":9,"owasp_score":11,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"google\/gemini-3.1-flash-lite-image","name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","created":1782837225,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","architecture":{"modality":"text+image->text+image","input_modalities":["image","text","pdf"],"output_modalities":["image","text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":58982},"pricing":{"prompt":"0.00000025","completion":"0.0000015","web_search":"0.014","discount":0},"context_length":65536,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}]}},{"id":"sakana\/fugu-ultra","name":"Sakana: Fugu Ultra","created":1782276303,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"expiration_date":null,"inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}]}},{"id":"google\/gemini-3.1-flash-image","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","created":1781754065,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google\u2019s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","architecture":{"modality":"text+image->text+image","input_modalities":["image","text","pdf"],"output_modalities":["image","text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000005","completion":"0.000003","web_search":"0.014","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}]}},{"id":"google\/gemini-3-pro-image","name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","created":1781754054,"description":"Nano Banana Pro is Google\u2019s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","architecture":{"modality":"text+image->text+image","input_modalities":["image","text","pdf"],"output_modalities":["image","text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":32768},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.000012","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"cohere\/north-mini-code:free","name":"Cohere: North Mini Code (free)","created":1781723748,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere"},"top_provider":{"is_moderated":true,"context_length":256000,"max_completion_tokens":64000},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":256000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["cohere"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"z-ai\/glm-5.2","name":"Z.ai: GLM 5.2","created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.53033708,"avgAttemptCostUsd":26.2141134},"inference_provider_ids":["alibaba","ambient","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","digitalocean","friendli","gmicloud","inceptron","mistral","morph","nebius","novita","parasail","relace","runware","siliconflow","streamlake","tencent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}]},"enkrypt":{"model_name":"glm-5.2","provider":"openai_compatible","source":"z-ai","risk_score":32.5842,"bias_score":86.3,"cbrn_score":50.67,"harmful_score":9.44,"insecure_code_score":13.78,"toxicity_score":2.73,"robustness_score":null,"jailbreak_score":29.0647,"evasion_score":null,"safety_score":40.016,"nist_score":33,"owasp_score":36,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"moonshotai\/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","created":1781266361,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.0000006","completion":"0.0000035","input_cache_read":"0.00000016"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.60674157,"avgAttemptCostUsd":32.940153},"inference_provider_ids":["alibaba","cloudflare","coreweave","gmicloud","inceptron","moonshotai","novita","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]},"enkrypt":{"model_name":"kimi-k2.7-code","provider":"openai_compatible","source":"moonshotai","risk_score":27.6738,"bias_score":84.24,"cbrn_score":42,"harmful_score":1.67,"insecure_code_score":7.56,"toxicity_score":2.91,"robustness_score":null,"jailbreak_score":21.5827,"evasion_score":null,"safety_score":37.2093,"nist_score":28,"owasp_score":31,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"alias_target":"anthropic\/claude-fable-5.2","id":"~anthropic\/claude-fable-latest","name":"Anthropic: Claude Fable Latest","created":1781029944,"description":"This model always redirects to the latest model in the Claude Fable family.","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000008","completion":"0.00004","input_cache_read":"0.0000002","input_cache_write":"0.00001","web_search":"0.01"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"anthropic\/claude-fable-5","name":"Anthropic: Claude Fable 5 ($$$$)","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.71011236,"avgAttemptCostUsd":87.5169082},"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]},"enkrypt":{"model_name":"claude-fable-5","provider":"anthropic","source":"anthropic","risk_score":0,"bias_score":0,"cbrn_score":0,"harmful_score":0,"insecure_code_score":0,"toxicity_score":0,"robustness_score":null,"jailbreak_score":0,"evasion_score":null,"safety_score":0,"nist_score":0,"owasp_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"nvidia\/nemotron-3.5-content-safety","name":"NVIDIA: Nemotron 3.5 Content Safety","created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":117964},"pricing":{"prompt":"0.0000002","completion":"0.0000002","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"nvidia\/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":202800,"max_completion_tokens":182520},"pricing":{"prompt":"0.0000004","completion":"0.00000176","input_cache_read":"0.00000008","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.19101124,"avgAttemptCostUsd":101.8186902},"inference_provider_ids":["baseten","deepinfra","kt","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}]},"enkrypt":{"model_name":"nemotron-3-ultra-550b-a55b","provider":"openai_compatible","source":"nvidia","risk_score":32.0435,"bias_score":87.34,"cbrn_score":52.67,"harmful_score":9.44,"insecure_code_score":6.22,"toxicity_score":4.55,"robustness_score":null,"jailbreak_score":27.1942,"evasion_score":null,"safety_score":41.7803,"nist_score":32,"owasp_score":35,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"nvidia\/nemotron-3-ultra-550b-a55b:free","name":"NVIDIA: Nemotron 3 Ultra (free)","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...\n\n**Terms of service** For NVIDIA free endpoints (Super\/Ultra\/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https:\/\/www.nvidia.com\/en-us\/about-nvidia\/privacy-policy\/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https:\/\/assets.ngc.nvidia.com\/products\/api-catalog\/legal\/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}]}},{"id":"qwen\/qwen3.7-plus","name":"Qwen: Qwen3.7 Plus","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000032","completion":"0.00000128","input_cache_read":"0.000000064","input_cache_write":"0.0000004","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"minimax\/minimax-m3","name":"MiniMax: MiniMax M3","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":524288,"max_completion_tokens":512000},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000006"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.47640449,"avgAttemptCostUsd":10.350343800000001},"inference_provider_ids":["coreweave","deepinfra","fireworks","gmicloud","minimax","nebius","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"minimax-m3","provider":"openai_compatible","source":"minimax","risk_score":31.3345,"bias_score":79.59,"cbrn_score":49.17,"harmful_score":5.56,"insecure_code_score":20,"toxicity_score":2.36,"robustness_score":null,"jailbreak_score":26.3309,"evasion_score":null,"safety_score":39.1339,"nist_score":31,"owasp_score":35,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"stepfun\/step-3.7-flash","name":"StepFun: Step 3.7 Flash","created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":230400},"pricing":{"prompt":"0.0000002","completion":"0.00000115","input_cache_read":"0.00000004","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["novita","stepfun"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"anthropic\/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.67640449,"avgAttemptCostUsd":85.194714},"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]},"enkrypt":{"model_name":"claude-opus-4-8","provider":"anthropic","source":"anthropic","risk_score":16.4467,"bias_score":48.06,"cbrn_score":8,"harmful_score":0.56,"insecure_code_score":24.89,"toxicity_score":0.73,"robustness_score":null,"jailbreak_score":3.02158,"evasion_score":null,"safety_score":21.9727,"nist_score":16,"owasp_score":21,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"qwen\/qwen3.7-max","name":"Qwen: Qwen3.7 Max","created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.000001475","completion":"0.000004425","input_cache_read":"0.000000295","input_cache_write":"0.00000184375","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.54606742,"avgAttemptCostUsd":20.6499772},"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"qwen3.7-max","provider":"openai_compatible","source":"qwen","risk_score":29.2787,"bias_score":74.42,"cbrn_score":49.83,"harmful_score":8.89,"insecure_code_score":8.89,"toxicity_score":4.36,"robustness_score":null,"jailbreak_score":26.9065,"evasion_score":null,"safety_score":36.8885,"nist_score":29,"owasp_score":32,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"x-ai\/grok-build-0.1","name":"SpaceXAI: Grok Build 0.1","created":1779298123,"description":"Grok Build 0.1 is SpaceXAI\u2019s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Grok"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":230400},"pricing":{"prompt":"0.000001","completion":"0.000002","input_cache_read":"0.0000002","web_search":"0.005","discount":0},"context_length":256000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.50561798,"avgAttemptCostUsd":30.701289600000003},"inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]},"enkrypt":{"model_name":"grok-build-0.1","provider":"openai_compatible","source":"xAI","risk_score":33.9681,"bias_score":84.75,"cbrn_score":46.5,"harmful_score":13.33,"insecure_code_score":12.89,"toxicity_score":12.36,"robustness_score":null,"jailbreak_score":27.7698,"evasion_score":null,"safety_score":42.903,"nist_score":34,"owasp_score":37,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"google\/gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000075","completion":"0.0000045","image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","web_search":"0.014","internal_reasoning":"0.0000045","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.64719101,"avgAttemptCostUsd":104.4912192},"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]},"enkrypt":{"model_name":"gemini-3.5-flash","provider":"openai_compatible","source":"google","risk_score":32.3289,"bias_score":80.36,"cbrn_score":52,"harmful_score":15,"insecure_code_score":11.56,"toxicity_score":2.73,"robustness_score":null,"jailbreak_score":30.6475,"evasion_score":null,"safety_score":38.332,"nist_score":32,"owasp_score":35,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"perceptron\/perceptron-mk1","name":"Perceptron: Perceptron Mk1","created":1778597029,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000015","completion":"0.0000015","discount":0},"context_length":32768,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["perceptron"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google\u2019s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","web_search":"0.014","internal_reasoning":"0.00000075","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}]}},{"id":"openai\/gpt-chat-latest","name":"OpenAI: GPT Chat Latest","created":1778000212,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"expiration_date":null,"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"x-ai\/grok-4.3","name":"SpaceXAI: Grok 4.3","created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Grok"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":900000},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002","web_search":"0.005","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}]},"enkrypt":{"model_name":"grok-4.3","provider":"xai","source":"xai","risk_score":31.3584,"bias_score":87.08,"cbrn_score":34.83,"harmful_score":5,"insecure_code_score":21.33,"toxicity_score":8.55,"robustness_score":null,"jailbreak_score":22.446,"evasion_score":null,"safety_score":39.6151,"nist_score":31,"owasp_score":36,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"mistralai\/mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":209715},"pricing":{"prompt":"0.0000015","completion":"0.0000075","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","high"]}]}},{"id":"nvidia\/nemotron-3-nano-omni-30b-a3b-reasoning:free","name":"NVIDIA: Nemotron 3 Nano Omni (free)","created":1777393095,"description":"NVIDIA Nemotron\u2122 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...\n\n**Terms of service** For NVIDIA free endpoints (Super\/Ultra\/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https:\/\/www.nvidia.com\/en-us\/about-nvidia\/privacy-policy\/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https:\/\/assets.ngc.nvidia.com\/products\/api-catalog\/legal\/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":65536},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":256000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"alias_target":"anthropic\/claude-haiku-5.5","id":"~anthropic\/claude-haiku-latest","name":"Anthropic: Claude Haiku Latest","created":1777318492,"description":"This model always redirects to the latest model in the Claude Haiku family.","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","web_search":"0.01"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"alias_target":"openai\/gpt-5.4-mini","id":"~openai\/gpt-mini-latest","name":"OpenAI: GPT Mini Latest","created":1777318471,"description":"This model always redirects to the latest model in the GPT Mini family.","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000075","completion":"0.0000045","input_cache_read":"0.000000075","web_search":"0.01"},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"alias_target":"google\/gemini-4-carbon","id":"~google\/gemini-pro-latest","name":"Google: Gemini Pro Latest","created":1777318451,"description":"This model always redirects to the latest model in the Gemini Pro family.","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.000002","completion":"0.00001","image":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","web_search":"0.014","internal_reasoning":"0.00001"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"alias_target":"moonshotai\/kimi-k3","id":"~moonshotai\/kimi-latest","name":"MoonshotAI: Kimi Latest","created":1777318428,"description":"This model always redirects to the latest model in the Kimi family.","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000001824","completion":"0.0000110055","input_cache_read":"0.00000018"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","amazon-bedrock","baseten","boundless","chutes","deepinfra","digitalocean","fireworks","inference-net","io-net","kt","makora","modal","moonshotai","morph","nebius","parasail","relace","river","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"alias_target":"google\/gemini-4-hydrogen","id":"~google\/gemini-flash-latest","name":"Google: Gemini Flash Latest","created":1777318398,"description":"This model always redirects to the latest model in the Gemini Flash family.","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"pricing":{"prompt":"0.0000015","completion":"0.0000075","image":"0.0000015","input_cache_read":"0.000000075","input_cache_write":"0.0000000833333333333333","web_search":"0.014","internal_reasoning":"0.0000075"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"alias_target":"anthropic\/claude-sonnet-5.5","id":"~anthropic\/claude-sonnet-latest","name":"Anthropic: Claude Sonnet Latest","created":1777318368,"description":"This model always redirects to the latest model in the Claude Sonnet family.","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","web_search":"0.01"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"qwen\/qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0.0000003","completion":"0.0000018","input_cache_write":"0.000000375","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0.0000001875","completion":"0.000001125","input_cache_write":"0.000000234375","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.0000001","completion":"0.0000009","input_cache_read":"0.000000025"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","alibaba","atlas-cloud","coreweave","darkbloom","deepinfra","dekallm","parasail","primeintellect","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities \u2014 accepting text, image, and video inputs...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":81920},"pricing":{"prompt":"0.00000045","completion":"0.0000027","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","chutes","deepinfra","reka","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro ($$$$)","created":1777051896,"description":"GPT-5.5 Pro is OpenAI\u2019s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"prompt":"gpt55"}},{"id":"openai\/gpt-5.5","name":"OpenAI: GPT-5.5","created":1777051893,"description":"GPT-5.5 is OpenAI\u2019s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.74157303,"avgAttemptCostUsd":72.62918640000001},"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"prompt":"gpt55"},"enkrypt":{"model_name":"gpt-5.5","provider":"openai","source":"","risk_score":19.2109,"bias_score":61.5,"cbrn_score":20.67,"harmful_score":0.56,"insecure_code_score":5.33,"toxicity_score":8,"robustness_score":null,"jailbreak_score":9.20863,"evasion_score":null,"safety_score":28.4683,"nist_score":19,"owasp_score":22,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"deepseek\/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":393216},"pricing":{"prompt":"0.0000016","completion":"0.0000032","input_cache_read":"0.000000135","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.44044944,"avgAttemptCostUsd":15.908566},"inference_provider_ids":["alibaba","atlas-cloud","azure","baidu","baseten","deepinfra","deepseek","digitalocean","gmicloud","novita","relace","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}]},"enkrypt":{"model_name":"deepseek-v4-pro","provider":"novita","source":"deepseek","risk_score":33.2118,"bias_score":85.27,"cbrn_score":17.33,"harmful_score":22.22,"insecure_code_score":33.78,"toxicity_score":7.45,"robustness_score":null,"jailbreak_score":9.06475,"evasion_score":null,"safety_score":42.3416,"nist_score":33,"owasp_score":39,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"deepseek\/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":393216},"pricing":{"prompt":"0.00000009","completion":"0.00000018","input_cache_read":"0.000000018"},"context_length":1048576,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","azure","baidu","baseten","deepinfra","digitalocean","fireworks","gmicloud","mancer","novita","parasail","relace","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}]},"enkrypt":{"model_name":"deepseek-v4-flash","provider":"novita","source":"deepseek","risk_score":36.2603,"bias_score":85.27,"cbrn_score":29.67,"harmful_score":23.33,"insecure_code_score":34.67,"toxicity_score":8.36,"robustness_score":null,"jailbreak_score":21.0072,"evasion_score":null,"safety_score":42.3416,"nist_score":36,"owasp_score":41,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"tencent\/hy3-preview","name":"Tencent: Hy3 preview","created":1776878150,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.00000018","completion":"0.0000006","input_cache_read":"0.00000006","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","low","high"]}]}},{"id":"xiaomi\/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi\u2019s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1024000,"max_completion_tokens":131072},"pricing":{"prompt":"0.000000435","completion":"0.00000087","input_cache_read":"0.0000000036","discount":0},"context_length":1024000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.47640449,"avgAttemptCostUsd":4.9236556},"inference_provider_ids":["atlas-cloud","digitalocean"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"mimo-v2.5-pro","provider":"openai_compatible","source":"xiaomi","risk_score":27.8866,"bias_score":71.06,"cbrn_score":47,"harmful_score":2.22,"insecure_code_score":17.33,"toxicity_score":1.82,"robustness_score":null,"jailbreak_score":24.4604,"evasion_score":null,"safety_score":35.2847,"nist_score":28,"owasp_score":31,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"xiaomi\/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000008","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5.4-image-2","name":"OpenAI: GPT-5.4 Image 2","created":1776797528,"description":"[GPT-5.4](https:\/\/openrouter.ai\/openai\/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file","pdf"],"output_modalities":["image","text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":272000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000008","completion":"0.000015","input_cache_read":"0.000002","web_search":"0.01","discount":0},"context_length":272000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","top_logprobs","verbosity"],"expiration_date":null,"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"alias_target":"anthropic\/claude-opus-5.5","id":"~anthropic\/claude-opus-latest","name":"Anthropic: Claude Opus Latest","created":1776795361,"description":"This model always redirects to the latest model in the Claude Opus family.","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000002","input_cache_write":"0.000005","web_search":"0.01"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"moonshotai\/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI\/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.00000065","completion":"0.00000341","input_cache_read":"0.00000015"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"terminalBench":{"overallScore":0.54382022,"avgAttemptCostUsd":24.844050600000003},"inference_provider_ids":["atlas-cloud","baidu","chutes","cloudflare","coreweave","crusoe","deepinfra","digitalocean","inceptron","moonshotai","novita","parasail","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"kimi-k2.6","provider":"openai_compatible","source":"moonshotai","risk_score":29.2868,"bias_score":71.32,"cbrn_score":48.5,"harmful_score":9.44,"insecure_code_score":12.44,"toxicity_score":4.73,"robustness_score":null,"jailbreak_score":27.0504,"evasion_score":null,"safety_score":36.0866,"nist_score":29,"owasp_score":32,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"anthropic\/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.7011236,"avgAttemptCostUsd":100.5076156},"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"},"verbosity":"xhigh"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]},"enkrypt":{"model_name":"claude-opus-4-7","provider":"anthropic","source":"anthropic","risk_score":19.9881,"bias_score":76.49,"cbrn_score":3.67,"harmful_score":0.56,"insecure_code_score":17.78,"toxicity_score":1.45,"robustness_score":null,"jailbreak_score":1.72662,"evasion_score":null,"safety_score":28.4683,"nist_score":20,"owasp_score":26,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"z-ai\/glm-5.1","name":"Z.ai: GLM 5.1 (retires Nov 20)","created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":182476},"pricing":{"prompt":"0.0000014","completion":"0.0000044","input_cache_read":"0.00000026","discount":0},"context_length":204800,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":"2026-11-20","terminalBench":{"overallScore":0.49438202,"avgAttemptCostUsd":23.9824468},"inference_provider_ids":["alibaba","atlas-cloud","baidu","chutes","friendli","gmicloud","novita","siliconflow","streamlake","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"glm-5.1","provider":"novita","source":"zai-org","risk_score":24.4588,"bias_score":76.49,"cbrn_score":21,"harmful_score":8.89,"insecure_code_score":11.56,"toxicity_score":4.36,"robustness_score":null,"jailbreak_score":11.5108,"evasion_score":null,"safety_score":32.7185,"nist_score":24,"owasp_score":28,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"google\/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference \u2014 delivering near-31B quality at...","architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.00000002","completion":"0.00000006","input_cache_read":"0.00000001","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","cloudflare","coreweave","darkbloom","deepinfra","dekallm","gmicloud","google-vertex","io-net","makora","nextbit","novita","parasail","primeintellect","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"gemma-4-26B-A4B-it","provider":"openai_compatible","source":"google","risk_score":28.5312,"bias_score":87.08,"cbrn_score":37,"harmful_score":5,"insecure_code_score":10.67,"toxicity_score":2.91,"robustness_score":null,"jailbreak_score":21.8705,"evasion_score":null,"safety_score":36.5678,"nist_score":29,"owasp_score":33,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"google\/gemma-4-31b-it","name":"Google: Gemma 4 31B","created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking\/reasoning mode, native function...","architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":16384},"pricing":{"prompt":"0.0000001","completion":"0.00000034","input_cache_read":"0.0000001","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["chutes","coreweave","crusoe","deepinfra","dekallm","friendli","gmicloud","kt","modal","nextbit","novita","parasail","primeintellect","sambanova","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"gemma-4-31B-it","provider":"openai_compatible","source":"google","risk_score":29.4562,"bias_score":91.47,"cbrn_score":33.33,"harmful_score":6.11,"insecure_code_score":12,"toxicity_score":4.36,"robustness_score":null,"jailbreak_score":19.4245,"evasion_score":null,"safety_score":38.5726,"nist_score":29,"owasp_score":34,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"qwen\/qwen3.6-plus","name":"Qwen: Qwen3.6 Plus","created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000325","completion":"0.00000195","input_cache_write":"0.00000040625","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"z-ai\/glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","created":1775061458,"description":"GLM-5V-Turbo is Z.ai\u2019s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024"},"context_length":202752,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"x-ai\/grok-4.20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","created":1774979158,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI\u2019s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Grok"},"top_provider":{"is_moderated":false,"context_length":2000000,"max_completion_tokens":1800000},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002","web_search":"0.005","discount":0},"context_length":2000000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"x-ai\/grok-4.20","name":"SpaceXAI: Grok 4.20","created":1774979019,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Grok"},"top_provider":{"is_moderated":false,"context_length":2000000,"max_completion_tokens":1800000},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002","web_search":"0.005","discount":0},"context_length":2000000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/lyria-3-pro-preview","name":"Google: Lyria 3 Pro Preview","created":1774907286,"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...","architecture":{"modality":"text+image->text+audio","input_modalities":["text","image"],"output_modalities":["text","audio"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"google\/lyria-3-clip-preview","name":"Google: Lyria 3 Clip Preview","created":1774907255,"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...","architecture":{"modality":"text+image->text+audio","input_modalities":["text","image"],"output_modalities":["text","audio"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0","completion":"0","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"rekaai\/reka-edge","name":"Reka Edge","created":1774026965,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image\/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":16384,"max_completion_tokens":14745},"pricing":{"prompt":"0.0000001","completion":"0.0000001","discount":0},"context_length":16384,"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["reka"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"minimax\/minimax-m2.7","name":"MiniMax: MiniMax M2.7","created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":196608,"max_completion_tokens":176947},"pricing":{"prompt":"0.00000021","completion":"0.00000084","input_cache_read":"0.000000042"},"context_length":196608,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["gmicloud","groq","minimax","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]},"enkrypt":{"model_name":"minimax-m2.7","provider":"novita","source":"minimax","risk_score":13.0815,"bias_score":45.48,"cbrn_score":15,"harmful_score":2.22,"insecure_code_score":0.89,"toxicity_score":1.82,"robustness_score":null,"jailbreak_score":2.15827,"evasion_score":null,"safety_score":21.4114,"nist_score":13,"owasp_score":15,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000002","completion":"0.00000125","input_cache_read":"0.00000002","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"id":"openai\/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000075","completion":"0.0000045","input_cache_read":"0.000000075","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"id":"mistralai\/mistral-small-2603","name":"Mistral: Mistral Small 4","created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":209715},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","high"]}]}},{"id":"z-ai\/glm-5-turbo","name":"Z.ai: GLM 5 Turbo","created":1773583573,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000012","completion":"0.000004","input_cache_read":"0.00000024"},"context_length":202752,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"glm-5-turbo","provider":"openrouter","source":"zai-org","risk_score":27.8652,"bias_score":88.11,"cbrn_score":24,"harmful_score":11.11,"insecure_code_score":11.56,"toxicity_score":4.55,"robustness_score":null,"jailbreak_score":13.6691,"evasion_score":null,"safety_score":36.9687,"nist_score":28,"owasp_score":32,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"nvidia\/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000006","completion":"0.00000032","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","deepinfra","dekallm"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium"]}]}},{"id":"bytedance-seed\/seed-2.0-lite","name":"ByteDance Seed: Seed-2.0-Lite","created":1773157231,"description":"Seed-2.0-Lite is a versatile, cost\u2011efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000025","completion":"0.000002","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}]}},{"id":"qwen\/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":40960},"pricing":{"prompt":"0.000000023","completion":"0.000000034","input_cache_read":"0.000000021"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["darkbloom","deepinfra","parasail","primeintellect","siliconflow","together"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro ($$$$)","created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00003","completion":"0.00018","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}]}},{"id":"openai\/gpt-5.4","name":"OpenAI: GPT-5.4","created":1772734352,"description":"GPT-5.4 is OpenAI\u2019s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000025","completion":"0.000015","input_cache_read":"0.00000025","web_search":"0.01","discount":0},"context_length":1050000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"id":"google\/gemini-3.1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","created":1772512673,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","web_search":"0.014","internal_reasoning":"0.00000075","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}]}},{"id":"bytedance-seed\/seed-2.0-mini","name":"ByteDance Seed: Seed-2.0-Mini","created":1772131107,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal\/low\/medium\/high), multimodal understanding,...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000001","completion":"0.0000004","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}]}},{"id":"google\/gemini-3.1-flash-image-preview","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","created":1772119558,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google\u2019s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","architecture":{"modality":"text+image->text+image","input_modalities":["image","text","pdf"],"output_modalities":["image","text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":58982},"pricing":{"prompt":"0.0000005","completion":"0.000003","web_search":"0.014","discount":0},"context_length":65536,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}]}},{"id":"qwen\/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","created":1772053822,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":81920},"pricing":{"prompt":"0.0000001625","completion":"0.0000013","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","darkbloom","deepinfra","parasail","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"qwen3.5-35b-a3b","provider":"novita","source":"qwen","risk_score":22.3043,"bias_score":73.39,"cbrn_score":26.83,"harmful_score":1.67,"insecure_code_score":8,"toxicity_score":1.64,"robustness_score":null,"jailbreak_score":13.3813,"evasion_score":null,"safety_score":30.6335,"nist_score":22,"owasp_score":26,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"qwen\/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":81920},"pricing":{"prompt":"0.000000195","completion":"0.00000156","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","chutes","deepinfra","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"qwen3.5-27b","provider":"novita","source":"qwen","risk_score":20.0536,"bias_score":60.47,"cbrn_score":28.83,"harmful_score":1.11,"insecure_code_score":6.22,"toxicity_score":3.64,"robustness_score":null,"jailbreak_score":13.9568,"evasion_score":null,"safety_score":27.7466,"nist_score":20,"owasp_score":23,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"qwen\/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000026","completion":"0.00000208","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"qwen3.5-122b-a10b","provider":"novita","source":"qwen","risk_score":20.4986,"bias_score":59.69,"cbrn_score":29.83,"harmful_score":2.22,"insecure_code_score":7.11,"toxicity_score":3.64,"robustness_score":null,"jailbreak_score":14.1007,"evasion_score":null,"safety_score":28.2277,"nist_score":20,"owasp_score":23,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"qwen\/qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000065","completion":"0.00000026","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","created":1772045923,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","audio","image","video","file","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","web_search":"0.014","internal_reasoning":"0.000012","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"openai\/gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","created":1771959164,"description":"GPT-5.3-Codex is OpenAI\u2019s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.000000175","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"id":"aion-labs\/aion-2.0","name":"AionLabs: Aion-2.0","created":1771881306,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000008","completion":"0.0000016","input_cache_read":"0.0000002","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"google\/gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google\u2019s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","web_search":"0.014","internal_reasoning":"0.000006","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"anthropic\/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","input_cache_write":"0.00000375","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"expiration_date":null,"terminalBench":{"overallScore":0.5505618,"avgAttemptCostUsd":53.374126600000004},"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}]},"enkrypt":{"model_name":"claude-sonnet-4-6","provider":"anthropic","source":"anthropic","risk_score":32.4787,"bias_score":81.14,"cbrn_score":15.33,"harmful_score":0.56,"insecure_code_score":32.89,"toxicity_score":null,"robustness_score":null,"jailbreak_score":null,"evasion_score":null,"safety_score":null,"nist_score":32,"owasp_score":39,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"qwen\/qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000026","completion":"0.00000156","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":64000},"pricing":{"prompt":"0.00000039","completion":"0.00000234","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba","atlas-cloud","deepinfra","gmicloud","novita","parasail","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"qwen3.5-397b-a17b","provider":"novita","source":"qwen","risk_score":17.0427,"bias_score":49.61,"cbrn_score":24.5,"harmful_score":2.78,"insecure_code_score":5.78,"toxicity_score":2.55,"robustness_score":null,"jailbreak_score":11.6547,"evasion_score":null,"safety_score":23.2558,"nist_score":17,"owasp_score":19,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"minimax\/minimax-m2.5","name":"MiniMax: MiniMax M2.5","created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":198000,"max_completion_tokens":32768},"pricing":{"prompt":"0.00000027","completion":"0.00000095","input_cache_read":"0.00000003"},"context_length":198000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","atlas-cloud","digitalocean","gmicloud","minimax","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"z-ai\/glm-5","name":"Z.ai: GLM 5","created":1770829182,"description":"GLM-5 is Z.ai\u2019s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":131072},"pricing":{"prompt":"0.000001","completion":"0.0000032","input_cache_read":"0.0000002"},"context_length":204800,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","baidu","gmicloud","novita","siliconflow","streamlake","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"anthropic\/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","created":1770219050,"description":"Opus 4.6 is Anthropic\u2019s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"},"verbosity":"low"},"medium":{"reasoning":{"enabled":true,"effort":"medium"},"verbosity":"medium"},"high":{"reasoning":{"enabled":true,"effort":"high"},"verbosity":"high"},"max":{"reasoning":{"enabled":true,"effort":"max"},"verbosity":"max"}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}]}},{"id":"qwen\/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.00000012","completion":"0.0000008","input_cache_read":"0.00000007"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"moonshotai\/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.0000006","completion":"0.000003","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","atlas-cloud","novita","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"kimi-k2.5","provider":"novita","source":"moonshotai","risk_score":26.3715,"bias_score":83.72,"cbrn_score":33.17,"harmful_score":5.56,"insecure_code_score":5.78,"toxicity_score":3.64,"robustness_score":null,"jailbreak_score":20.7194,"evasion_score":null,"safety_score":33.8412,"nist_score":26,"owasp_score":30,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"writer\/palmyra-x5","name":"Writer: Palmyra X5","created":1769003823,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":1040000,"max_completion_tokens":8192},"pricing":{"prompt":"0.0000006","completion":"0.000006","discount":0},"context_length":1040000,"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-audio","name":"OpenAI: GPT Audio","created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio","pdf"],"output_modalities":["text","audio"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.0000025","completion":"0.00001","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"openai\/gpt-audio-mini","name":"OpenAI: GPT Audio Mini","created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio","pdf"],"output_modalities":["text","audio"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.0000006","completion":"0.0000024","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"z-ai\/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":117964},"pricing":{"prompt":"0.0000000605","completion":"0.0000004"},"context_length":200000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","cloudflare","novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","created":1768409315,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","architecture":{"modality":"text+image->text","input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.000000175","web_search":"0.01"},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"z-ai\/glm-4.7","name":"Z.ai: GLM 4.7","created":1766378014,"description":"GLM-4.7 is Z.ai\u2019s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning\/execution. It demonstrates significant improvements in executing complex agent tasks while...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000004","completion":"0.00000175","input_cache_read":"0.00000008"},"context_length":204800,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","deepinfra","mancer","novita","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025","input_cache_read":"0.000000025","input_cache_write":"0.0000000416666666666667","web_search":"0.014","internal_reasoning":"0.0000015","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}]}},{"id":"nvidia\/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.00000006","completion":"0.00000024","input_cache_read":"0.000000012","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["nebius"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro ($$$$)","created":1765389780,"description":"GPT-5.2 Pro is OpenAI\u2019s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000021","completion":"0.000168","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}]}},{"id":"openai\/gpt-5.2","name":"OpenAI: GPT-5.2","created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000175","completion":"0.000014","input_cache_read":"0.000000175","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}]},"enkrypt":{"model_name":"gpt-5.2","provider":"openai","source":"","risk_score":16.0341,"bias_score":58.4,"cbrn_score":10.17,"harmful_score":8.33,"insecure_code_score":0,"toxicity_score":3.27,"robustness_score":null,"jailbreak_score":4.02878,"evasion_score":null,"safety_score":23.4162,"nist_score":16,"owasp_score":19,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"mistralai\/devstral-2512","name":"Mistral: Devstral 2 2512","created":1765285419,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":209715},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"relace\/relace-search","name":"Relace: Relace Search","created":1765213560,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000001","completion":"0.000003","discount":0},"context_length":256000,"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["relace"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"z-ai\/glm-4.6v","name":"Z.ai: GLM 4.6V","created":1765207462,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.000000055"},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","created":1764878934,"description":"GPT-5.1-Codex-Max is OpenAI\u2019s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","architecture":{"modality":"text+image->text","input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.000000125","web_search":"0.01"},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"amazon\/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Nova"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":65535},"pricing":{"prompt":"0.0000003","completion":"0.0000025","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"mistralai\/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","created":1764681735,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":209715},"pricing":{"prompt":"0.0000002","completion":"0.0000002","input_cache_read":"0.00000002","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":209715},"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":104857},"pricing":{"prompt":"0.0000001","completion":"0.0000001","input_cache_read":"0.00000001","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/mistral-large-2512","name":"Mistral: Mistral Large 3 2512","created":1764624472,"description":"Mistral Large 3 2512 is Mistral\u2019s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":209715},"pricing":{"prompt":"0.0000005","completion":"0.0000015","input_cache_read":"0.00000005","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"deepseek\/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","created":1764594642,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":147456},"pricing":{"prompt":"0.00000026","completion":"0.00000038","input_cache_read":"0.00000013"},"context_length":163840,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","atlas-cloud","baidu","deepinfra","digitalocean","gmicloud","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"anthropic\/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","created":1764010580,"description":"Claude Opus 4.5 is Anthropic\u2019s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":200000,"max_completion_tokens":64000},"pricing":{"prompt":"0.000005","completion":"0.000025","input_cache_read":"0.0000005","input_cache_write":"0.00000625","web_search":"0.01","discount":0},"context_length":200000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","verbosity"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-3-pro-image-preview","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","created":1763653797,"description":"Nano Banana Pro is Google\u2019s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","architecture":{"modality":"text+image->text+image","input_modalities":["image","text","pdf"],"output_modalities":["image","text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":32768},"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","web_search":"0.014","internal_reasoning":"0.000006","discount":0},"context_length":65536,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"openai\/gpt-5.1","name":"OpenAI: GPT-5.1","created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.000000125","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}]},"enkrypt":{"model_name":"gpt-5.1","provider":"openai","source":"","risk_score":17.4611,"bias_score":56.33,"cbrn_score":6.5,"harmful_score":16.11,"insecure_code_score":4,"toxicity_score":4.36,"robustness_score":null,"jailbreak_score":7.19424,"evasion_score":null,"safety_score":21.5718,"nist_score":17,"owasp_score":20,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","created":1763060298,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","architecture":{"modality":"text+image->text","input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.00000013","web_search":"0.01"},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"openai\/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","created":1763057820,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","architecture":{"modality":"text+image->text","input_modalities":["image","text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000025","completion":"0.000002","input_cache_read":"0.00000003","web_search":"0.01"},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"moonshotai\/kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI\u2019s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":98304},"pricing":{"prompt":"0.0000006","completion":"0.0000025","input_cache_read":"0.00000015"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]},"enkrypt":{"model_name":"kimi-k2-thinking","provider":"novita","source":"moonshotai","risk_score":28.0702,"bias_score":67.44,"cbrn_score":24.33,"harmful_score":26.11,"insecure_code_score":19.56,"toxicity_score":2.91,"robustness_score":null,"jailbreak_score":11.6456,"evasion_score":null,"safety_score":31.676,"nist_score":28,"owasp_score":31,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"amazon\/nova-premier-v1","name":"Amazon: Nova Premier 1.0","created":1761950332,"description":"Amazon Nova Premier is the most capable of Amazon\u2019s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":32000},"pricing":{"prompt":"0.0000025","completion":"0.0000125","input_cache_read":"0.000000625","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"perplexity\/sonar-pro-search","name":"Perplexity: Sonar Pro Search","created":1761854366,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":8000},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.018","discount":0},"context_length":200000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"mistralai\/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","created":1761835144,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","architecture":{"modality":"text+file+audio->text","input_modalities":["text","audio","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":26214},"pricing":{"prompt":"0.0000001","completion":"0.0000003","input_cache_read":"0.00000001","discount":0},"context_length":32768,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","created":1761752836,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000075","completion":"0.0000003","input_cache_read":"0.0000000375","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","groq"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]},"enkrypt":{"model_name":"gpt-oss-safeguard-20b","provider":"groq","source":"openai","risk_score":25.7241,"bias_score":74.42,"cbrn_score":18,"harmful_score":25.56,"insecure_code_score":7.56,"toxicity_score":3.09,"robustness_score":null,"jailbreak_score":17.1223,"evasion_score":null,"safety_score":28.6287,"nist_score":26,"owasp_score":29,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini (retires Dec 1)","created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https:\/\/openrouter.ai\/openai\/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","architecture":{"modality":"text+image+file->text+image","input_modalities":["file","image","text","pdf"],"output_modalities":["image","text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000025","completion":"0.000002","input_cache_read":"0.00000025","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"expiration_date":"2026-12-01","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"anthropic\/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic\u2019s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4\u2019s performance...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":200000,"max_completion_tokens":64000},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.0000001","input_cache_write":"0.00000125","web_search":"0.01","discount":0},"context_length":200000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","created":1760463308,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.00000025","completion":"0.00000075","input_cache_read":"0.00000012"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-5-image","name":"OpenAI: GPT-5 Image ($$$$)","created":1760447986,"description":"[GPT-5](https:\/\/openrouter.ai\/openai\/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file","pdf"],"output_modalities":["image","text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00001","completion":"0.00001","input_cache_read":"0.00000125","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"expiration_date":"2026-12-11","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"google\/gemini-2.5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","created":1759870431,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","architecture":{"modality":"text+image->text+image","input_modalities":["image","text","pdf"],"output_modalities":["image","text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":8192},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","web_search":"0.014","internal_reasoning":"0.0000025","discount":0},"context_length":32768,"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-5-pro","name":"OpenAI: GPT-5 Pro ($$$$)","created":1759776663,"description":"GPT-5 Pro is OpenAI\u2019s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000015","completion":"0.00012","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":"2026-12-11","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["high"]}]}},{"id":"z-ai\/glm-4.6","name":"Z.ai: GLM 4.6","created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":202752,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000005","completion":"0.000002","input_cache_read":"0.0000001"},"context_length":204800,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","novita","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"glm-4.6","provider":"novita","source":"zai-org","risk_score":36.7101,"bias_score":87.34,"cbrn_score":25.33,"harmful_score":45,"insecure_code_score":21.33,"toxicity_score":4.55,"robustness_score":null,"jailbreak_score":20.7194,"evasion_score":null,"safety_score":40.0962,"nist_score":37,"owasp_score":40,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"anthropic\/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic\u2019s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":1000000,"max_completion_tokens":64000},"pricing":{"prompt":"0.000003","completion":"0.000015","input_cache_read":"0.0000003","input_cache_write":"0.00000375","web_search":"0.01","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"deepseek\/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":147456},"pricing":{"prompt":"0.00000027","completion":"0.00000041"},"context_length":163840,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"deepseek-v3.2-exp","provider":"novita","source":"deepseek","risk_score":34.5025,"bias_score":77,"cbrn_score":18.5,"harmful_score":53.33,"insecure_code_score":18.22,"toxicity_score":5.45,"robustness_score":null,"jailbreak_score":23.8849,"evasion_score":null,"safety_score":32.8789,"nist_score":34,"owasp_score":37,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"thedrummer\/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":117964},"pricing":{"prompt":"0.0000003","completion":"0.0000005","input_cache_read":"0.00000015","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"relace\/relace-apply-3","name":"Relace: Relace Apply 3","created":1758891572,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000085","completion":"0.00000125","discount":0},"context_length":256000,"per_request_limits":null,"supported_parameters":["max_tokens","seed","stop"],"expiration_date":null,"inference_provider_ids":["relace"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart\/table...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":32768},"pricing":{"prompt":"0.00000021","completion":"0.0000019","input_cache_read":"0.0000001"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"qwen3-vl-235b-a22b-instruct","provider":"novita","source":"qwen","risk_score":26.9573,"bias_score":72.61,"cbrn_score":17.5,"harmful_score":29.44,"insecure_code_score":9.78,"toxicity_score":5.45,"robustness_score":null,"jailbreak_score":18.1295,"evasion_score":null,"safety_score":29.2702,"nist_score":27,"owasp_score":30,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"deepseek\/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](\/deepseek\/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":147456},"pricing":{"prompt":"0.00000027","completion":"0.000001"},"context_length":163840,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000195","completion":"0.000000975","input_cache_read":"0.000000039","input_cache_write":"0.00000024375","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without \u201cthinking\u201d traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000009","completion":"0.0000011"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","google-vertex","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"moonshotai\/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai\/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":98304},"pricing":{"prompt":"0.0000006","completion":"0.0000025"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"nousresearch\/hermes-4-405b","name":"Nous: Hermes 4 405B","created":1756235463,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":117964},"pricing":{"prompt":"0.000001","completion":"0.000003","input_cache_read":"0.0000002","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["nebius"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"deepseek\/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":147456},"pricing":{"prompt":"0.00000025","completion":"0.00000095","input_cache_read":"0.00000013"},"context_length":163840,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["coreweave","deepinfra","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"mistralai\/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":104857},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"z-ai\/glm-4.5v","name":"Z.ai: GLM 4.5V","created":1754922288,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":16384},"pricing":{"prompt":"0.0000006","completion":"0.0000018","input_cache_read":"0.00000011"},"context_length":65536,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":"2026-12-31","inference_provider_ids":["novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5","name":"OpenAI: GPT-5 (retires Dec 11)","created":1754587413,"description":"GPT-5 is OpenAI\u2019s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.000000125","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":"2026-12-11","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]},"enkrypt":{"model_name":"gpt-5","provider":"openai","source":"OpenAI","risk_score":11.7922,"bias_score":40.05,"cbrn_score":7.11,"harmful_score":6.67,"insecure_code_score":2.22,"toxicity_score":2.91,"robustness_score":null,"jailbreak_score":2.07317,"evasion_score":null,"safety_score":14.389,"nist_score":12,"owasp_score":14,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-5-mini","name":"OpenAI: GPT-5 Mini (retires Dec 11)","created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000025","completion":"0.000002","input_cache_read":"0.000000025","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":"2026-12-11","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]},"enkrypt":{"model_name":"gpt-5-mini","provider":"openai","source":"OpenAI","risk_score":15.7763,"bias_score":58.91,"cbrn_score":3.17,"harmful_score":8.89,"insecure_code_score":3.11,"toxicity_score":4.8,"robustness_score":null,"jailbreak_score":2.57576,"evasion_score":null,"safety_score":16.0232,"nist_score":16,"owasp_score":19,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-5-nano","name":"OpenAI: GPT-5 Nano (retires Dec 11)","created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000005","completion":"0.0000004","input_cache_read":"0.000000005","web_search":"0.01","discount":0},"context_length":400000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"expiration_date":"2026-12-11","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]},"enkrypt":{"model_name":"gpt-5-nano","provider":"openai","source":"OpenAI","risk_score":14.9257,"bias_score":60.98,"cbrn_score":2,"harmful_score":7.22,"insecure_code_score":1.33,"toxicity_score":3.09,"robustness_score":null,"jailbreak_score":1.85567,"evasion_score":null,"safety_score":14.334,"nist_score":15,"owasp_score":18,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":65536},"pricing":{"prompt":"0.00000003","completion":"0.00000015","input_cache_read":"0.000000015","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","amazon-bedrock","baseten","cerebras","coreweave","crusoe","deepinfra","dekallm","digitalocean","google-vertex","groq","io-net","mancer","near-ai","nebius","parasail","primeintellect","sail-research","sambanova","siliconflow","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]},"enkrypt":{"model_name":"gpt-oss-120b","provider":"fireworks","source":"OpenAI","risk_score":20.1454,"bias_score":60.21,"cbrn_score":13.83,"harmful_score":14.44,"insecure_code_score":1.33,"toxicity_score":10.91,"robustness_score":null,"jailbreak_score":18.8679,"evasion_score":null,"safety_score":24.8614,"nist_score":20,"owasp_score":22,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":117964},"pricing":{"prompt":"0.000000018","completion":"0.00000009","input_cache_read":"0.000000009","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","amazon-bedrock","coreweave","darkbloom","deepinfra","dekallm","groq","parasail","primeintellect","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]},"enkrypt":{"model_name":"gpt-oss-20b","provider":"fireworks","source":"OpenAI","risk_score":27.6703,"bias_score":72.35,"cbrn_score":19,"harmful_score":19.44,"insecure_code_score":7.56,"toxicity_score":20,"robustness_score":null,"jailbreak_score":27.1698,"evasion_score":null,"safety_score":31.9778,"nist_score":28,"owasp_score":30,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"anthropic\/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1 ($$$$)","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic\u2019s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file","pdf"],"output_modalities":["text"],"tokenizer":"Claude"},"top_provider":{"is_moderated":true,"context_length":200000,"max_completion_tokens":32000},"pricing":{"prompt":"0.000015","completion":"0.000075","input_cache_read":"0.0000015","input_cache_write":"0.00001875","web_search":"0.01"},"context_length":200000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"anthropic","variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"mistralai\/codestral-2508","name":"Mistral: Codestral 2508","created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https:\/\/mistral.ai\/news\/codestral-25-08)","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":204800},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000003","discount":0},"context_length":256000,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","created":1753972379,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":true,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"context_length":262144,"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"pricing":{"prompt":"0.0000001","completion":"0.0000003","input_cache_read":"0.0000001"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["dekallm","nebius","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"z-ai\/glm-4.5","name":"Z.ai: GLM 4.5","created":1753471347,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":98304},"pricing":{"prompt":"0.0000006","completion":"0.0000022","input_cache_read":"0.00000011"},"context_length":131072,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":"2026-12-31","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"glm-4.5","provider":"novita","source":"zai-org","risk_score":36.1503,"bias_score":69.51,"cbrn_score":22.33,"harmful_score":47.78,"insecure_code_score":36.89,"toxicity_score":4.24,"robustness_score":null,"jailbreak_score":17.8333,"evasion_score":null,"safety_score":36.9792,"nist_score":36,"owasp_score":40,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"z-ai\/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","created":1753471258,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":98304},"pricing":{"prompt":"0.0000002","completion":"0.0000011","input_cache_read":"0.00000003"},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["novita","siliconflow","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","created":1753449557,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000045","completion":"0.0000035"},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"qwen\/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":65536},"pricing":{"prompt":"0.0000003","completion":"0.000001","input_cache_read":"0.0000001"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","google-vertex","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"bytedance\/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":2048},"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.0000001","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"google\/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65535},"pricing":{"prompt":"0.00000005","completion":"0.0000002","image":"0.00000005","input_cache_read":"0.000000005","input_cache_write":"0.0000000416666666666667","web_search":"0.014","internal_reasoning":"0.0000002","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":117964},"pricing":{"prompt":"0.00000014","completion":"0.0000008","input_cache_read":"0.00000005"},"context_length":262144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","google-vertex","nebius","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"moonshotai\/kimi-k2","name":"MoonshotAI: Kimi K2 0711","created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":98304},"pricing":{"prompt":"0.00000057","completion":"0.0000023"},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"cognitivecomputations\/dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","created":1752094966,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an \u201cuncensored\u201d instruct-tuned LLM, preserving...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":8192},"pricing":{"prompt":"0.0000002","completion":"0.0000009"},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","stop","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"morph\/morph-v3-large","name":"Morph: Morph V3 Large","created":1751910858,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens\/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}<\/instruction> <code>{initial_code}<\/code>...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000009","completion":"0.0000019","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"expiration_date":null,"inference_provider_ids":["morph"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"morph\/morph-v3-fast","name":"Morph: Morph V3 Fast","created":1751910002,"description":"Morph's fastest apply model for code edits. ~10,500 tokens\/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}<\/instruction> <code>{initial_code}<\/code> <update>{edit_snippet}<\/update>...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000008","completion":"0.0000012","discount":0},"context_length":262144,"per_request_limits":null,"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"expiration_date":null,"inference_provider_ids":["morph"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":26214},"pricing":{"prompt":"0.0000001","completion":"0.0000003","input_cache_read":"0.00000001","discount":0},"context_length":256000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","mistral","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"google\/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["file","image","text","audio","video","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65535},"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","web_search":"0.014","internal_reasoning":"0.00000125","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"gemini-2.5-flash","provider":"gemini","source":"Google","risk_score":32.0541,"bias_score":75.16,"cbrn_score":15.83,"harmful_score":45.37,"insecure_code_score":15.38,"toxicity_score":8.52,"robustness_score":null,"jailbreak_score":27.1429,"evasion_score":null,"safety_score":32.1138,"nist_score":32,"owasp_score":35,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"google\/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","created":1750169544,"description":"Gemini 2.5 Pro is Google\u2019s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs \u201cthinking\u201d capabilities, enabling it to reason through responses with enhanced accuracy...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","web_search":"0.014","internal_reasoning":"0.000005","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]},"enkrypt":{"model_name":"gemini-2.5-pro","provider":"gemini","source":"Google","risk_score":35.8097,"bias_score":61.15,"cbrn_score":20.83,"harmful_score":54.63,"insecure_code_score":38.46,"toxicity_score":3.98,"robustness_score":null,"jailbreak_score":31.0714,"evasion_score":null,"safety_score":32.5203,"nist_score":36,"owasp_score":39,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/o3-pro","name":"OpenAI: o3 Pro ($$$$)","created":1749598352,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","architecture":{"modality":"text+image+file->text","input_modalities":["text","file","image","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":200000,"max_completion_tokens":100000},"pricing":{"prompt":"0.00002","completion":"0.00008","web_search":"0.01","discount":0},"context_length":200000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"expiration_date":"2026-12-11","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"google\/gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","created":1749137257,"description":"Gemini 2.5 Pro is Google\u2019s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs \u201cthinking\u201d capabilities, enabling it to reason through responses with enhanced accuracy...","architecture":{"modality":"text+image+file+audio->text","input_modalities":["file","image","text","audio","pdf"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":65536},"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","web_search":"0.014","internal_reasoning":"0.000005","discount":0},"context_length":1048576,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"deepseek\/deepseek-r1-0528","name":"DeepSeek: R1 0528","created":1748455170,"description":"May 28th update to the [original DeepSeek R1](\/deepseek\/deepseek-r1) Performance on par with [OpenAI o1](\/openai\/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000005","completion":"0.00000215","input_cache_read":"0.00000035"},"context_length":163840,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","siliconflow","streamlake"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]},"enkrypt":{"model_name":"deepseek-r1-0528","provider":"fireworks","source":"accounts","risk_score":52.4164,"bias_score":74.94,"cbrn_score":53.5,"harmful_score":57.78,"insecure_code_score":73.78,"toxicity_score":2.09,"robustness_score":null,"jailbreak_score":27.1711,"evasion_score":null,"safety_score":24.8069,"nist_score":52,"owasp_score":57,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"mistralai\/mistral-medium-3","name":"Mistral: Mistral Medium 3","created":1746627341,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8\u00d7 lower cost...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":104857},"pricing":{"prompt":"0.0000004","completion":"0.000002","input_cache_read":"0.00000004","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"meta-llama\/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":163840,"max_completion_tokens":16384},"pricing":{"prompt":"0.000000144","completion":"0.000000144","discount":0},"context_length":163840,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","created":1745878604,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":40960,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000012","completion":"0.0000005"},"context_length":40960,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"qwen3-30b-a3b","provider":"fireworks","source":"Qwen","risk_score":49.6461,"bias_score":91.47,"cbrn_score":55.67,"harmful_score":61.67,"insecure_code_score":37.33,"toxicity_score":2.09,"robustness_score":null,"jailbreak_score":27.1053,"evasion_score":null,"safety_score":24.9517,"nist_score":50,"owasp_score":53,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"qwen\/qwen3-14b","name":"Qwen: Qwen3 14B","created":1745876478,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":40960,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000012","completion":"0.00000024"},"context_length":40960,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"qwen\/qwen3-32b","name":"Qwen: Qwen3 32B","created":1745875945,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3"},"top_provider":{"is_moderated":false,"context_length":40960,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000008","completion":"0.00000028"},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","deepinfra","siliconflow","tenstorrent"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/o3","name":"OpenAI: o3 (retires Dec 11)","created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":200000,"max_completion_tokens":100000},"pricing":{"prompt":"0.000002","completion":"0.000008","input_cache_read":"0.0000005","web_search":"0.01","discount":0},"context_length":200000,"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"expiration_date":"2026-12-11","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]},"enkrypt":{"model_name":"o3","provider":"openai","source":"OpenAI","risk_score":20.9692,"bias_score":77,"cbrn_score":9.67,"harmful_score":6.11,"insecure_code_score":7.11,"toxicity_score":4.95,"robustness_score":null,"jailbreak_score":2.03947,"evasion_score":null,"safety_score":22.249,"nist_score":21,"owasp_score":25,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-4.1","name":"OpenAI: GPT-4.1","created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1047576,"max_completion_tokens":32768},"pricing":{"prompt":"0.000002","completion":"0.000008","input_cache_read":"0.0000005","web_search":"0.01","discount":0},"context_length":1047576,"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"},"enkrypt":{"model_name":"gpt-4.1","provider":"openai","source":"OpenAI","risk_score":26.7472,"bias_score":82.17,"cbrn_score":10,"harmful_score":25,"insecure_code_score":11.11,"toxicity_score":5.45,"robustness_score":null,"jailbreak_score":7.17105,"evasion_score":null,"safety_score":22.1525,"nist_score":27,"owasp_score":31,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":1047576,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000004","completion":"0.0000016","input_cache_read":"0.0000001","web_search":"0.01","discount":0},"context_length":1047576,"per_request_limits":null,"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"},"enkrypt":{"model_name":"gpt-4.1-mini","provider":"openai","source":"OpenAI","risk_score":31.3871,"bias_score":84.5,"cbrn_score":11.33,"harmful_score":41.67,"insecure_code_score":14.67,"toxicity_score":4.77,"robustness_score":null,"jailbreak_score":10.7895,"evasion_score":null,"safety_score":21.4286,"nist_score":31,"owasp_score":35,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","created":1744651369,"description":"For tasks that demand low latency, GPT\u20114.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":1047576,"max_completion_tokens":942818},"pricing":{"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000003","web_search":"0.01"},"context_length":1047576,"per_request_limits":null,"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"},"enkrypt":{"model_name":"gpt-4.1-nano","provider":"openai","source":"OpenAI","risk_score":30.7776,"bias_score":87.08,"cbrn_score":10.5,"harmful_score":40,"insecure_code_score":12.44,"toxicity_score":3.86,"robustness_score":null,"jailbreak_score":9.67105,"evasion_score":null,"safety_score":21.139,"nist_score":31,"owasp_score":35,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"meta-llama\/llama-4-maverick","name":"Meta: Llama 4 Maverick","created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4"},"top_provider":{"is_moderated":false,"context_length":524288,"max_completion_tokens":32768},"pricing":{"prompt":"0.00000035","completion":"0.000001","input_cache_read":"0.00000017","discount":0},"context_length":524288,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","google-vertex","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"meta-llama\/llama-4-scout","name":"Meta: Llama 4 Scout","created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4"},"top_provider":{"is_moderated":false,"context_length":327680,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000008","completion":"0.00000024","discount":0},"context_length":1310720,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","deepinfra","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"deepseek\/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](\/deepseek\/deepseek-chat-v3) model and performs really well...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":115200},"pricing":{"prompt":"0.00000029","completion":"0.00000114","input_cache_read":"0.00000011"},"context_length":163840,"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["gmicloud","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":102400},"pricing":{"prompt":"0.000000351","completion":"0.000000555"},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"google\/gemma-3-4b-it","name":"Google: Gemma 3 4B","created":1741905510,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000004","completion":"0.00000005","input_cache_read":"0.00000002","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"gemma-3-4b-it","provider":"openai_compatible","source":"google","risk_score":39.109,"bias_score":83.98,"cbrn_score":11.5,"harmful_score":51.11,"insecure_code_score":44,"toxicity_score":4.95,"robustness_score":null,"jailbreak_score":10.8553,"evasion_score":null,"safety_score":25.5309,"nist_score":39,"owasp_score":45,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"google\/gemma-3-12b-it","name":"Google: Gemma 3 12B","created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000004","completion":"0.00000012","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"gemma-3-12b-it","provider":"openai_compatible","source":"google","risk_score":35.3775,"bias_score":86.82,"cbrn_score":9.33,"harmful_score":47.22,"insecure_code_score":31.56,"toxicity_score":1.95,"robustness_score":null,"jailbreak_score":7.96053,"evasion_score":null,"safety_score":22.6834,"nist_score":35,"owasp_score":40,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"cohere\/command-a","name":"Cohere: Command A","created":1741894342,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":true,"context_length":256000,"max_completion_tokens":8192},"pricing":{"prompt":"0.0000025","completion":"0.00001","discount":0},"context_length":256000,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"rekaai\/reka-flash-3","name":"Reka Flash 3","created":1741812813,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":58982},"pricing":{"prompt":"0.0000001","completion":"0.0000002","discount":0},"context_length":65536,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["reka"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"google\/gemma-3-27b-it","name":"Google: Gemma 3 27B","created":1741756359,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":117964},"pricing":{"prompt":"0.000000064","completion":"0.000000128","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","nebius","nextbit","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"gemma-3-27b-it","provider":"openai_compatible","source":"google","risk_score":35.0275,"bias_score":82.95,"cbrn_score":9.67,"harmful_score":43.89,"insecure_code_score":36,"toxicity_score":2.64,"robustness_score":null,"jailbreak_score":7.03947,"evasion_score":null,"safety_score":23.6486,"nist_score":35,"owasp_score":40,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"thedrummer\/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":29491},"pricing":{"prompt":"0.00000055","completion":"0.0000008","input_cache_read":"0.00000025","discount":0},"context_length":32768,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"perplexity\/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","created":1741313308,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https:\/\/docs.perplexity.ai\/guides\/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":115200},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.005","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"perplexity\/sonar-pro","name":"Perplexity: Sonar Pro","created":1741312423,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https:\/\/docs.perplexity.ai\/guides\/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":8000},"pricing":{"prompt":"0.000003","completion":"0.000015","web_search":"0.005","discount":0},"context_length":200000,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"perplexity\/sonar-deep-research","name":"Perplexity: Sonar Deep Research","created":1741311246,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":115200},"pricing":{"prompt":"0.000002","completion":"0.000008","web_search":"0.005","internal_reasoning":"0.000003","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[]}},{"id":"mistralai\/mistral-saba","name":"Mistral: Saba","created":1739803239,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":26214},"pricing":{"prompt":"0.0000002","completion":"0.0000006","input_cache_read":"0.00000002","discount":0},"context_length":32768,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"aion-labs\/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","created":1738696718,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other\u2019s responses. It is a fine-tuned base model...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":29491},"pricing":{"prompt":"0.0000008","completion":"0.0000016","discount":0},"context_length":32768,"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":115200},"pricing":{"prompt":"0.0000008","completion":"0.000001","input_cache_read":"0.0000004"},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen-plus","name":"Qwen: Qwen-Plus","created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":32768},"pricing":{"prompt":"0.00000026","completion":"0.00000078","input_cache_read":"0.000000052","input_cache_write":"0.000000325","discount":0},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000005","completion":"0.00000008"},"context_length":32768,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"Mistral-Small-24B-Instruct-2501","provider":"Together","source":"Mistral","risk_score":39.5529,"bias_score":84.75,"cbrn_score":9.33,"harmful_score":54.44,"insecure_code_score":45.78,"toxicity_score":3.45,"robustness_score":null,"jailbreak_score":9.60526,"evasion_score":null,"safety_score":24.8552,"nist_score":40,"owasp_score":45,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"perplexity\/sonar","name":"Perplexity: Sonar","created":1738013808,"description":"Sonar is lightweight, affordable, fast, and simple to use \u2014 now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":127072,"max_completion_tokens":114364},"pricing":{"prompt":"0.000001","completion":"0.000001","web_search":"0.005","discount":0},"context_length":127072,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"microsoft\/phi-4","name":"Microsoft: Phi 4","created":1736489872,"description":"[Microsoft Research](\/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":16384,"max_completion_tokens":14745},"pricing":{"prompt":"0.000000056","completion":"0.000000112","discount":0},"context_length":16384,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"phi-4","provider":"HuggingFace","source":"Microsoft","risk_score":21.6711,"bias_score":83.2,"cbrn_score":5,"harmful_score":3.33,"insecure_code_score":16,"toxicity_score":0.82,"robustness_score":null,"jailbreak_score":2.17105,"evasion_score":null,"safety_score":18.2915,"nist_score":22,"owasp_score":28,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"deepseek\/deepseek-chat","name":"DeepSeek: DeepSeek V3","created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":16000},"pricing":{"prompt":"0.0000002574","completion":"0.0000010287"},"context_length":163840,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","streamlake"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"deepseek-chat","provider":"deepseek","source":"deepseek-chat","risk_score":33.7785,"bias_score":85.27,"cbrn_score":8.83,"harmful_score":41.67,"insecure_code_score":26.67,"toxicity_score":6.45,"robustness_score":null,"jailbreak_score":9.07895,"evasion_score":null,"safety_score":25.1931,"nist_score":34,"owasp_score":38,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"cohere\/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","created":1734158152,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":4000},"pricing":{"prompt":"0.0000000375","completion":"0.00000015","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"command-r7b-12-2024","provider":"cohere","source":"Cohere","risk_score":40.632,"bias_score":99.48,"cbrn_score":28.67,"harmful_score":55,"insecure_code_score":15.56,"toxicity_score":4.45,"robustness_score":null,"jailbreak_score":12.1053,"evasion_score":null,"safety_score":29.1988,"nist_score":41,"owasp_score":44,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"meta-llama\/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","created":1733506137,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in\/text out). The Llama 3.3 instruction tuned text only model...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":115200},"pricing":{"prompt":"0.0000001","completion":"0.00000032","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["akashml","amazon-bedrock","cloudflare","coreweave","deepinfra","google-vertex","groq","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"amazon\/nova-lite-v1","name":"Amazon: Nova Lite 1.0","created":1733437363,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova"},"top_provider":{"is_moderated":true,"context_length":300000,"max_completion_tokens":5120},"pricing":{"prompt":"0.00000006","completion":"0.00000024","discount":0},"context_length":300000,"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"amazon\/nova-micro-v1","name":"Amazon: Nova Micro 1.0","created":1733437237,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nova"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":5120},"pricing":{"prompt":"0.000000035","completion":"0.00000014","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"amazon\/nova-pro-v1","name":"Amazon: Nova Pro 1.0","created":1733436303,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova"},"top_provider":{"is_moderated":true,"context_length":300000,"max_completion_tokens":5120},"pricing":{"prompt":"0.0000008","completion":"0.0000032","discount":0},"context_length":300000,"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It\u2019s also better at working with uploaded...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"mistralai\/mistral-large-2407","name":"Mistral Large 2407","created":1731978415,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https:\/\/mistral.ai\/news\/mistral-large-2407\/)....","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":104857},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"qwen\/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":29491},"pricing":{"prompt":"0.00000066","completion":"0.000001"},"context_length":32768,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"thedrummer\/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","created":1731103448,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":1024000,"max_completion_tokens":819200},"pricing":{"prompt":"0.0000004","completion":"0.0000004","discount":0},"context_length":1024000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"anthracite-org\/magnum-v4-72b","name":"Magnum v4 72B","created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https:\/\/openrouter.ai\/anthropic\/claude-3.5-sonnet) and Opus(https:\/\/openrouter.ai\/anthropic\/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https:\/\/openrouter.ai\/qwen\/qwen-2.5-72b-instruct).","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":4096},"pricing":{"prompt":"0.0000025","completion":"0.000005","input_cache_read":"0.0000025","discount":0},"context_length":32768,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"meta-llama\/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct (retires Nov 20)","created":1727222400,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3"},"top_provider":{"is_moderated":false,"context_length":60000,"max_completion_tokens":54000},"pricing":{"prompt":"0.000000027","completion":"0.000000201","discount":0},"context_length":60000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"expiration_date":"2026-11-20","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"Llama-3.2-1B-Instruct","provider":"Hugging Face","source":"meta","risk_score":37.4762,"bias_score":95.87,"cbrn_score":11.67,"harmful_score":8.89,"insecure_code_score":69.78,"toxicity_score":1.18,"robustness_score":null,"jailbreak_score":3.22368,"evasion_score":null,"safety_score":28.5232,"nist_score":37,"owasp_score":48,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"meta-llama\/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct (retires Nov 20)","created":1727222400,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3"},"top_provider":{"is_moderated":false,"context_length":80000,"max_completion_tokens":72000},"pricing":{"prompt":"0.00000005","completion":"0.00000033","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":"2026-11-20","inference_provider_ids":["cloudflare","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"Llama-3.2-3B-Instruct","provider":"Hugging Face","source":"meta","risk_score":38.3222,"bias_score":88.89,"cbrn_score":14.33,"harmful_score":15,"insecure_code_score":68.89,"toxicity_score":4.5,"robustness_score":null,"jailbreak_score":7.96053,"evasion_score":null,"safety_score":28.4749,"nist_score":38,"owasp_score":48,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"qwen\/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen"},"top_provider":{"is_moderated":false,"context_length":32768,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000036","completion":"0.0000004"},"context_length":32768,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"cohere\/command-r-08-2024","name":"Cohere: Command R (08-2024)","created":1724976000,"description":"command-r-08-2024 is an update of the [Command R](\/models\/cohere\/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":4000},"pricing":{"prompt":"0.00000015","completion":"0.0000006","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"cohere\/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","created":1724976000,"description":"command-r-plus-08-2024 is an update of the [Command R+](\/models\/cohere\/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":4000},"pricing":{"prompt":"0.0000025","completion":"0.00001","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"command-r-plus-08-2024","provider":"cohere","source":"Cohere","risk_score":52.9355,"bias_score":98.71,"cbrn_score":9.17,"harmful_score":60,"insecure_code_score":86.67,"toxicity_score":10.14,"robustness_score":null,"jailbreak_score":6.71053,"evasion_score":null,"safety_score":41.5541,"nist_score":53,"owasp_score":62,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"sao10k\/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https:\/\/ko-fi.com\/sao10k). It is the successor of [Euryale L3 70B v2.1](\/models\/sao10k\/l3-euryale-70b).","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000068","completion":"0.00000068","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"sao10k\/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3"},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":7372},"pricing":{"prompt":"0.00000004","completion":"0.00000005","discount":0},"context_length":8192,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https:\/\/openai.com\/index\/introducing-structured-outputs-in-the-api\/). GPT-4o (\"o\" for \"omni\") is...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"},"enkrypt":{"model_name":"gpt-4o-2024-08-06","provider":"openai","source":"OpenAI","risk_score":25.9949,"bias_score":79.33,"cbrn_score":6.17,"harmful_score":32.22,"insecure_code_score":10.67,"toxicity_score":1.59,"robustness_score":null,"jailbreak_score":5.19737,"evasion_score":null,"safety_score":18.4363,"nist_score":26,"owasp_score":30,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"meta-llama\/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3"},"top_provider":{"is_moderated":true,"context_length":131072,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000072","completion":"0.00000072","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["max_tokens","stop","temperature","tool_choice","tools","top_k","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"meta-llama\/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["amazon-bedrock","cloudflare","coreweave","deepinfra","groq","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"Llama-3.1-8B-Instruct","provider":"openai_compatible","source":"meta","risk_score":38.2035,"bias_score":81.65,"cbrn_score":16.17,"harmful_score":26.67,"insecure_code_score":50.67,"toxicity_score":15.86,"robustness_score":null,"jailbreak_score":25.3947,"evasion_score":null,"safety_score":25.9653,"nist_score":38,"owasp_score":44,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"mistralai\/mistral-nemo","name":"Mistral: Mistral Nemo","created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015","discount":0},"context_length":131072,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["deepinfra","dekallm","io-net","mistral","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](\/models\/openai\/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"},"enkrypt":{"model_name":"gpt-4o-mini","provider":"OpenAI","source":"OpenAI","risk_score":30.8832,"bias_score":86.3,"cbrn_score":8,"harmful_score":39.44,"insecure_code_score":18.67,"toxicity_score":2,"robustness_score":null,"jailbreak_score":5.85526,"evasion_score":null,"safety_score":21.7181,"nist_score":31,"owasp_score":35,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](\/models\/openai\/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000075","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"google\/gemma-2-27b-it","name":"Google: Gemma 2 27B","created":1720828800,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](\/models?q=gemini). Gemma models are well-suited for a variety of...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Gemini"},"top_provider":{"is_moderated":false,"context_length":8192,"max_completion_tokens":2048},"pricing":{"prompt":"0.00000065","completion":"0.00000065","discount":0},"context_length":8192,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"expiration_date":null,"inference_provider_ids":["nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{},"enkrypt":{"model_name":"gemma-2-27b-it","provider":"together","source":"google","risk_score":21.6434,"bias_score":68.22,"cbrn_score":10.33,"harmful_score":26.11,"insecure_code_score":3.56,"toxicity_score":0,"robustness_score":null,"jailbreak_score":6.11842,"evasion_score":null,"safety_score":24.1611,"nist_score":22,"owasp_score":24,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-4o","name":"OpenAI: GPT-4o","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](\/models\/openai\/gpt-4-turbo) while being twice as...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":true,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.0000025","completion":"0.00001","input_cache_read":"0.00000125","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"},"enkrypt":{"model_name":"gpt-4o","provider":"OpenAI","source":"OpenAI","risk_score":25.7279,"bias_score":83.46,"cbrn_score":5.5,"harmful_score":26.67,"insecure_code_score":11.56,"toxicity_score":1.45,"robustness_score":null,"jailbreak_score":3.68421,"evasion_score":null,"safety_score":19.5946,"nist_score":26,"owasp_score":30,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](\/models\/openai\/gpt-4-turbo) while being twice as...","architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":4096},"pricing":{"prompt":"0.000005","completion":"0.000015"},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"mistralai\/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","created":1713312000,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](\/models\/mistralai\/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":65536,"max_completion_tokens":52428},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0},"context_length":65536,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/mistral-large","name":"Mistral Large","created":1708905600,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https:\/\/mistral.ai\/news\/mistral-large-2407\/)....","architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":102400},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.0000002","discount":0},"context_length":128000,"per_request_limits":null,"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"expiration_date":null,"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","architecture":{"modality":"text->text","input_modalities":["text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":4095,"max_completion_tokens":3685},"pricing":{"prompt":"0.000001","completion":"0.000002"},"context_length":4095,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"openai\/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","architecture":{"modality":"text->text","input_modalities":["text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":16385,"max_completion_tokens":4096},"pricing":{"prompt":"0.000003","completion":"0.000004"},"context_length":16385,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"mancer\/weaver","name":"Mancer: Weaver (alpha)","created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay\/narrative situations.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2"},"top_provider":{"is_moderated":false,"context_length":8000,"max_completion_tokens":6000},"pricing":{"prompt":"0.0000003","completion":"0.0000005","input_cache_read":"0.0000003","discount":0},"context_length":8000,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"undi95\/remm-slerp-l2-13b","name":"ReMM SLERP 13B","created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2"},"top_provider":{"is_moderated":false,"context_length":6144,"max_completion_tokens":5529},"pricing":{"prompt":"0.0000003","completion":"0.0000005","input_cache_read":"0.0000002","discount":0},"context_length":6144,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"gryphe\/mythomax-l2-13b","name":"MythoMax 13B","created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2"},"top_provider":{"is_moderated":false,"context_length":4096,"max_completion_tokens":3686},"pricing":{"prompt":"0.00000008","completion":"0.00000011","discount":0},"context_length":8192,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["mancer","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-4","name":"OpenAI: GPT-4 ($$$$)","created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","architecture":{"modality":"text->text","input_modalities":["text","pdf"],"output_modalities":["text"],"tokenizer":"GPT"},"top_provider":{"is_moderated":false,"context_length":8191,"max_completion_tokens":4096},"pricing":{"prompt":"0.00003","completion":"0.00006"},"context_length":8191,"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"},"enkrypt":{"model_name":"gpt-4","provider":"OpenAI","source":"OpenAI","risk_score":27.3327,"bias_score":84.75,"cbrn_score":8.67,"harmful_score":19.44,"insecure_code_score":16.89,"toxicity_score":6.91,"robustness_score":null,"jailbreak_score":4.47368,"evasion_score":null,"safety_score":25.917,"nist_score":27,"owasp_score":32,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openrouter\/auto","name":"OpenRouter Auto Router","created":1793885889,"description":"Auto is OpenRouter\u2019s flagship model router, built for general-purpose usage. It adapts to each request, choosing cost-optimal models and adjusting reasoning effort. It balances task difficulty, benchmark results, live prices,...","architecture":{"modality":"text+image+file+audio+video->text+image","input_modalities":["text","image","audio","file","video"],"output_modalities":["text","image"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"pricing":{"prompt":"-1","completion":"-1"},"context_length":2000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","prediction","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","web_search_options"],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openrouter\/auto-code","name":"OpenRouter Auto Code","created":1793884321,"description":"Auto Code is OpenRouter\u2019s router built specifically for coding agents and harnesses. It uses the same routing engine as the [Auto Router](https:\/\/openrouter.ai\/openrouter\/auto), with every request treated as part of an...","architecture":{"modality":"text+image+file+audio+video->text+image","input_modalities":["text","image","audio","file","video"],"output_modalities":["text","image"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":64000},"pricing":{"prompt":"-1","completion":"-1"},"context_length":2000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"typesafe\/jev-router","name":"TypeSafe: Jev Router","created":1790363560,"description":"Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https:\/\/openrouter.ai\/~typesafe\/jev-latest), TypeSafe's first System One model, and adapts as your...","architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":64000},"pricing":{"prompt":"-1","completion":"-1"},"context_length":1000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"nvidia\/switchyard","name":"NVIDIA: Switchyard","created":1790025947,"description":"Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"pricing":{"prompt":"-1","completion":"-1"},"context_length":1000000,"per_request_limits":null,"supported_parameters":[],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openrouter\/auto-beta","name":"OpenRouter Auto Router (Beta)","created":1784311165,"description":"The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...","architecture":{"modality":"text+image+file+audio+video->text+image","input_modalities":["text","image","audio","file","video"],"output_modalities":["text","image"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":64000},"pricing":{"prompt":"-1","completion":"-1"},"context_length":2000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openrouter\/fusion","name":"OpenRouter: Fusion","created":1781371647,"description":"Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"pricing":{"prompt":"-1","completion":"-1"},"context_length":1000000,"per_request_limits":null,"supported_parameters":[],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openrouter\/pareto-code","name":"OpenRouter Pareto Code Router","created":1776747900,"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https:\/\/artificialanalysis.ai\/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https:\/\/openrouter.ai\/docs\/guides\/routing\/routers\/pareto-router#the-min_coding_score-parameter) to control how...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"pricing":{"prompt":"-1","completion":"-1"},"context_length":2000000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openrouter\/free","name":"OpenRouter Free Models Router","created":1769917427,"description":"The simplest way to get free inference. openrouter\/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"pricing":{"prompt":"0","completion":"0"},"context_length":200000,"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{}},{"id":"openrouter\/bodybuilder","name":"OpenRouter Body Builder (beta)","created":1764903653,"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router"},"top_provider":{"is_moderated":false,"context_length":null,"max_completion_tokens":null},"pricing":{"prompt":"-1","completion":"-1"},"context_length":128000,"per_request_limits":null,"supported_parameters":[],"expiration_date":null,"inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"paperinstruments\/ultramarine-1-flash","name":"Ultramarine 1 Flash","created":1794441600,"description":"Ultramarine 1 Flash is an open-weight multimodal reasoning model from Paper Instruments, post-trained from GLM-5.3 Flash for knowledge work in enterprise operations, finance, law, and consulting. It supports long-context document analysis and agentic workflows.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131000},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["fireworks"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}]}},{"id":"deepseek\/deepseek-v4.1-flash-1017-ultrafast","name":"DeepSeek: DeepSeek V4.1 Flash 1017 Ultrafast","created":1793923200,"description":"DeepSeek V4.1 Flash 1017 Ultrafast serves the October 17, 2026 update of DeepSeek V4.1 Flash through Fireworks' accelerated serverless endpoint. It supports text and image input, configurable reasoning, tool calling, structured outputs, and automatic prefix caching. Available in public preview without a waitroom or session time limit.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":1048576},"pricing":{"prompt":"0.0000024","completion":"0.0000096","input_cache_read":"0.000000048"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["fireworks"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}]}},{"id":"humansand\/ampersand-v0.1","name":"Ampersand v0.1","created":1793923200,"description":"Ampersand v0.1 is a collaborator model from Humans& for shared goals, group conversations, and long-running collaboration. Its Responses API supports text, reasoning, client-side function tools, and implicit prompt caching.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":32768},"pricing":{"prompt":"0","completion":"0"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["humansand"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}]}},{"id":"meituan\/longcat-2.5","name":"Meituan: LongCat 2.5","created":1793577600,"description":"LongCat 2.5 is Meituan\u2019s native multimodal model for coding and long-running agent workflows. It combines visual understanding with multi-step reasoning and tool use to work across complex codebases and full-project development. Its 1M-token context window supports tasks involving large documents, codebases, and text and image inputs.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.000000006"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["meituan"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"inclusionai\/ling-3.1-flash-1019","name":"inclusionAI: Ling 3.1 Flash 1019","created":1793318400,"description":"Ling 3.1 Flash 1019 is InclusionAI's updated hybrid reasoning language model for coding, multi-step analysis, and tool-using agents. Its mixture-of-experts architecture has 560B total parameters with 25B active per token, and its 1M-token context window supports long-document analysis and extended agentic workflows.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":262144},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000006"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"particle\/particle-1","name":"Particle-1","created":1793145600,"description":"Particle-1 is Particle AI\u2019s model for agentic coding and software engineering, post-trained on DeepSeek V4.1 Flash to complete tasks with fewer tokens. It supports text and image inputs, reasoning, tool use, and implicit prompt caching.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0.000000125","completion":"0.0000005","input_cache_read":"0.000000015"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["particle-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}]}},{"id":"openai\/gpt-6.1-terra-fast","name":"OpenAI: GPT-6.1 Terra (Fast)","created":1792972800,"description":"GPT-6.1 Terra is OpenAI\u2019s model for visual reasoning, precise computer use, and natural writing. It accepts text and images and generates text, with configurable reasoning effort, structured outputs, tool calling through the Responses API, and implicit and explicit prompt caching.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025"},"context_length":1050000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"moonshotai\/kimi-k3.1-pro-highspeed","name":"MoonshotAI: Kimi K3.1 Pro Highspeed","created":1792713600,"description":"Kimi K3.1 Pro Highspeed is Moonshot AI's most capable open-weight model, combining native vision with a 1-million-token context window for long-running coding and knowledge workflows that sustain context across large repositories, documents, and images.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":1048576},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000002","input_cache_write":"0.000005"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["amazon-bedrock","moonshotai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","high","max"]}]}},{"id":"scaledown\/scaledown-extract-1","name":"ScaleDown: Extract-1","created":1792454400,"description":"ScaleDown Extract-1 is a task-specific language model for extracting structured data from unstructured text using a custom JSON schema. It identifies domain-specific entities with confidence scores, character offsets, and surrounding context, and supports nested objects and arrays for workflows such as invoice processing, contract analysis, and record parsing.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":1000000},"pricing":{"prompt":"0.00000005","completion":"0"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","response_format","structured_outputs"],"inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{}},{"id":"scaledown\/scaledown-summarize-1","name":"ScaleDown: Summarize-1","created":1792454400,"description":"ScaleDown Summarize-1 is a task-specific language model for abstractive summarization of long documents, transcripts, and conversations. It rewrites source text into concise summaries and accepts instructions for format, language, length, and focus, making it useful for document processing, meeting summaries, and support workflows.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":1000},"pricing":{"prompt":"0.00000005","completion":"0"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop"],"inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{}},{"id":"inception\/mercury-3","name":"Mercury 3","created":1792368000,"description":"Mercury 3 is Inception\u2019s most capable model for agentic workflows and real-time applications. It is one of the world\u2019s fastest models, powered by diffusion.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000001","completion":"0.00000035","input_cache_read":"0.00000001"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"expiration_date":"2026-12-28","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"deepseek\/deepseek-v4.1-flash-1017-fast","name":"DeepSeek: DeepSeek V4.1 Flash 1017 Fast","created":1792195200,"description":"Higher-throughput variant of DeepSeek V4.1 Flash 1017 served by Baseten for multimodal reasoning, tool calling, and structured output, with automatic prefix caching.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":262144},"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.000000014"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["baseten"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}]}},{"id":"reflection\/beam-free","name":"Reflection: Beam 1.0 (Free)","created":1792108800,"description":"Beam is Reflection\u2019s reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"pricing":{"prompt":"0","completion":"0"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["reflection"],"isFree":true,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"callstack\/apex","name":"Apex","created":1791417600,"description":"Apex is Callstack\u2019s agentic coding model for mobile and web development, optimized for React Native, React, and Next.js. With a 256K context window, it supports feature development, debugging, code reviews, testing, and large refactors.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000005","completion":"0.000003","input_cache_read":"0.0000002"},"context_length":262144,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["callstack"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","xhigh"]}]}},{"id":"deepseek\/deepseek-v4.1-flash-fast","name":"DeepSeek: DeepSeek V4.1 Flash Fast","created":1790640000,"description":"Higher-throughput variant of DeepSeek V4.1 Flash for responsive coding, reasoning, and agentic workloads.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.000000014"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["baseten"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"openai\/gpt-6.1-sol-fast","name":"OpenAI: GPT-6.1 Sol (Fast)","created":1790640000,"description":"GPT-6.1 Sol is OpenAI's reasoning model for complex coding, computer use, and professional work. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support multi-step workflows.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000002","input_cache_write":"0.000005"},"context_length":1050000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6-luna-fast","name":"OpenAI: GPT-6 Luna (Fast)","created":1790035200,"description":"GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000002","completion":"0.000001","input_cache_read":"0.00000002","input_cache_write":"0.00000025"},"context_length":1050000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-6-sol-fast","name":"OpenAI: GPT-6 Sol (Fast)","created":1790035200,"description":"GPT-6 Sol is OpenAI's reasoning model for complex coding and agentic workflows. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools make it suited to software development and multi-step automation.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000004","input_cache_write":"0.000005"},"context_length":1050000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"quiverai\/arrow-2","name":"Arrow 2","created":1789516800,"description":"SVG generation model with agentic refinement and tool calling.","architecture":{"input_modalities":["text","image"],"output_modalities":["text","image"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":131072},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000004","input_cache_write":"0.000005"},"context_length":131072,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["quiverai"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"quiverai\/arrow-2-telos","name":"Arrow 2 Telos","created":1789516800,"description":"Higher-refinement Arrow 2 variant combining Arrow's speed with frontier-model reasoning.","architecture":{"input_modalities":["text","image"],"output_modalities":["text","image"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":131072},"pricing":{"prompt":"0.000006","completion":"0.00003","input_cache_read":"0.0000006","input_cache_write":"0.0000075"},"context_length":131072,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["quiverai"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}]}},{"id":"inclusionai\/ling-3.0-flash-sante","name":"inclusionAI: Ling 3.0 Flash Sante","created":1788480000,"description":"Ling-3.0-Flash-Sante is inclusionAI\u2019s language model specialized for health and medicine, built on a Mixture-of-Experts architecture with 124 billion total parameters and approximately 5.1 billion active per token. With a 256K context window and function calling, it supports medical knowledge reasoning, evidence-based retrieval, and complex medical workflows while retaining general reasoning, coding, and agentic capabilities.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":32000},"pricing":{"prompt":"0.000000075","completion":"0.00000022","input_cache_read":"0.000000015"},"context_length":256000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"openai\/gpt-6-astra-fast","name":"OpenAI: GPT-6 Astra (Fast) ($$$$)","created":1788480000,"description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00002","completion":"0.0001","input_cache_read":"0.000002","input_cache_write":"0.000025"},"context_length":1050000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}]}},{"id":"z-ai\/glm-5.3-fast","name":"Z.ai: GLM 5.3 Fast","created":1788307200,"description":"Speed-optimized version of Z.AI\u2019s GLM-5.3 agentic coding model, built for responsive, real-time workloads. It supports advanced coding, long-horizon task execution, testing, vulnerability discovery, and cybersecurity analysis, making it ideal for developer tools, coding agents, and complex multi-step engineering workflows.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":262144},"pricing":{"prompt":"0.0000021","completion":"0.0000066","input_cache_read":"0.00000021"},"context_length":1048576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["alibaba","baseten"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"inclusionai\/ling-3.0-flash-fin","name":"inclusionAI: Ling 3.0 Flash Fin","created":1787788800,"description":"Ling 3.0 Flash Fin is InclusionAI\u2019s finance-enhanced MoE language model, combining 124 billion total parameters with approximately 5.1 billion active parameters for efficient financial reasoning. Its 256K context window, function calling, and support for complex, multi-step investment workflows make it ideal for financial research, analysis, long-horizon planning, and execution, while retaining strong capabilities in coding and mathematics.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":32000},"pricing":{"prompt":"0.000000075","completion":"0.00000022","input_cache_read":"0.000000015"},"context_length":256000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"mixedbread\/toast-1","name":"Toast 1","created":1786579200,"description":"Built for knowledge-intensive questions, multi-step retrieval, and evidence synthesis. Toast 1 can work with any backend exposed through function calling.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131000,"max_completion_tokens":4000},"pricing":{"prompt":"0.0000003","completion":"0.00000072","input_cache_read":"0.000000036"},"context_length":131000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["mixedbread"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{}},{"id":"qwen\/qwen3.8-max","name":"Qwen: Qwen 3.8 Max","created":1785628800,"description":"Qwen 3.8 Max is a 2.4-trillion-parameter MoE model delivering a comprehensive leap in coding and professional work. Autonomously codes and delivers complete projects spanning 10+ days. Handles hundreds of specialized tasks across legal, financial, design, and other professional domains, producing production-grade results end-to-end in a single conversation. Native visual understanding runs through the full cycle of planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and extended video content. In long-horizon tasks, plans autonomously, iterates through closed feedback loops, and continuously evolves.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000002","completion":"0.000006","input_cache_read":"0.00000025","input_cache_write":"0.0000025"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["alibaba","fireworks"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}]},"enkrypt":{"model_name":"qwen3.8-max","provider":"openai_compatible","source":"qwen","risk_score":23.541,"bias_score":80.36,"cbrn_score":26,"harmful_score":0.56,"insecure_code_score":5.33,"toxicity_score":5.45,"robustness_score":null,"jailbreak_score":10.0719,"evasion_score":null,"safety_score":35.2847,"nist_score":24,"owasp_score":27,"ingestedAt":"2026-09-29T04:00:25.155Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"moonshotai\/kimi-k3-fast","name":"MoonshotAI: Kimi K3 Fast","created":1785110400,"description":"Fast version of Kimi\u2019s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":1000000},"pricing":{"prompt":"0.000006","completion":"0.0000225","input_cache_read":"0.0000006"},"context_length":1000000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["fireworks","morph"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}]}},{"id":"openai\/gpt-5.6-luna-fast","name":"OpenAI: GPT 5.6 Luna (Fast)","created":1783555200,"description":"GPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost in the series.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000004","completion":"0.0000024","input_cache_read":"0.00000004","input_cache_write":"0.0000005"},"context_length":1050000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-5.6-sol-fast","name":"OpenAI: GPT 5.6 Sol (Fast)","created":1783555200,"description":"GPT-5.6 Sol is the flagship of OpenAI's GPT-5.6 series, its most capable model for long-horizon agentic work across coding, biology, and cybersecurity.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000008","completion":"0.00004","input_cache_read":"0.0000008","input_cache_write":"0.00001"},"context_length":1050000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"openai\/gpt-5.6-terra-fast","name":"OpenAI: GPT 5.6 Terra (Fast)","created":1783555200,"description":"GPT-5.6 Terra is a balanced GPT-5.6 model for everyday work, with performance comparable to the previous generation at half the cost.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000004","completion":"0.000024","input_cache_read":"0.0000004","input_cache_write":"0.000005"},"context_length":1050000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}]}},{"id":"google\/gemini-omni-flash-preview","name":"Google: Gemini Omni Flash Preview","created":1782777600,"description":"Gemini Omni Flash (Preview) is a multimodal model designed for video, image, and text tasks. It is optimized for video generation, offering video output alongside text responses in a single model.","architecture":{"input_modalities":["text","image","pdf","video"],"output_modalities":["text","video"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":57920},"pricing":{"prompt":"0.0000015","completion":"0.000009"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]}},{"id":"z-ai\/glm-5.2-fast","name":"Z.ai: GLM 5.2 Fast","created":1782172800,"description":"GLM-5.2-Fast-Preview is the high-speed variant of Zhipu AI&#39;s GLM-5.2, with 1M context and capabilities on par with the standard version. Inference-optimized to deliver 1.5\u20132\u00d7 the output TPS, it fits latency-sensitive use cases such as real-time chat, multi-turn agents, and streaming code generation.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000028","completion":"0.0000088","input_cache_read":"0.00000056"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["alibaba","baseten"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"moonshotai\/kimi-k2.7-code-highspeed","name":"MoonshotAI: Kimi K2.7 Code High Speed","created":1781481600,"description":"Kimi K2.7 Code HighSpeed is the high-speed version of Kimi K2.7 Code, the same model as Kimi K2.7 Code, but with an output speed of approximately 180 Tokens\/s and up to 260 Tokens\/s in short context scenarios, delivering a more extreme coding experience.","architecture":{"input_modalities":["text","image","pdf","video"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000019","completion":"0.000008","input_cache_read":"0.00000038"},"context_length":262144,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["moonshotai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"tencent\/hy-mt2-lite","name":"Tencent: Tencent Hy-MT2-Lite","created":1781222400,"description":"Hy-MT2-Lite is Tencent Cloud Hunyuan\u2019s lightweight 1.8B translation model, combining efficient performance with an 8K-token context window and broad multilingual coverage. It supports translation across 33 languages and five ethnic Chinese and dialect variants, delivering strong results on benchmarks including FLORES-200 and WMT25. Designed for professional and real-world business use, it reliably follows instructions for structured, delimiter-preserving, context-aware, glossary-guided, and style-specific translation.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":8000,"max_completion_tokens":4000},"pricing":{"prompt":"0.000000044","completion":"0.000000177"},"context_length":8000,"supported_parameters":["max_tokens","temperature","stop"],"inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{}},{"id":"tencent\/hy-mt2-plus","name":"Tencent: Tencent Hy-MT2-Plus","created":1781222400,"description":"Hy-MT2-Plus is Tencent Cloud Hunyuan\u2019s 7B translation model, offering an 8K-token context window and broad multilingual coverage. Optimized for translation across 33 languages and five ethnic Chinese and dialect variants, it delivers industry-leading performance on benchmarks including FLORES-200 and WMT25. It excels in professional domains and real-world business scenarios, with strong instruction-following for structured, delimiter-preserving, context-aware, glossary-guided, and style-specific translation.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":8000,"max_completion_tokens":4000},"pricing":{"prompt":"0.000000074","completion":"0.000000295"},"context_length":8000,"supported_parameters":["max_tokens","temperature","stop","response_format","structured_outputs"],"inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{}},{"id":"tencent\/hy-mt2-pro","name":"Tencent: Tencent Hy-MT2-Pro","created":1779321600,"description":"Hy-MT2-Pro is Tencent Cloud Hunyuan\u2019s flagship translation model, featuring 30B-A3B parameters and an 8K-token context window. It delivers bidirectional translation across 33 core language pairs, plus five minority-language and dialect pairs. With industry-leading performance on FLORES-200 and WMT25, it excels in specialized domains and real-world business scenarios while supporting structured, contextual, terminology-aware, style-specific, and delimiter-preserving translation.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":8000,"max_completion_tokens":4000},"pricing":{"prompt":"0.000000074","completion":"0.000000295"},"context_length":8000,"supported_parameters":["max_tokens","temperature","stop","response_format","structured_outputs"],"inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{}},{"id":"openai\/gpt-5.5-fast","name":"OpenAI: GPT 5.5 (Fast) ($$$$)","created":1776988800,"description":"GPT\u20115.5 understands what you\u2019re trying to do faster and can carry more of the work itself. It excels at writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, operating software, and moving across tools until a task is finished. Instead of carefully managing every step, you can give GPT\u20115.5 a messy, multi-part task and trust it to plan, use tools, check its work, navigate through ambiguity, and keep going.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000125","completion":"0.000075","input_cache_read":"0.00000125"},"context_length":1000000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"prompt":"gpt55"}},{"id":"minimax\/minimax-m2.7-highspeed","name":"MiniMax: MiniMax M2.7 High Speed (retires Nov 18)","created":1773792000,"description":"M2.7 Highspeed: Same performance, faster and more agile (output speed approximately 100 tps)","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":204800,"max_completion_tokens":131100},"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000006","input_cache_write":"0.000000375"},"context_length":204800,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"expiration_date":"2026-11-18","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5.4-mini-fast","name":"OpenAI: GPT 5.4 Mini (Fast)","created":1773705600,"description":"GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000015","completion":"0.000009","input_cache_read":"0.00000015"},"context_length":400000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"id":"x-ai\/grok-4.20-multi-agent-beta","name":"SpaceXAI: Grok 4.20 Multi Agent Beta","created":1773187200,"description":"Multiple agents collaborate in parallel to perform deep research tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":2000000,"max_completion_tokens":2000000},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002"},"context_length":2000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"x-ai\/grok-4.20-non-reasoning-beta","name":"SpaceXAI: Grok 4.20 Beta Non-Reasoning","created":1773187200,"description":"Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":2000000,"max_completion_tokens":2000000},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002"},"context_length":2000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"x-ai\/grok-4.20-reasoning-beta","name":"SpaceXAI: Grok 4.20 Beta Reasoning","created":1773187200,"description":"Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":2000000,"max_completion_tokens":2000000},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002"},"context_length":2000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"x-ai\/grok-4.20-non-reasoning","name":"SpaceXAI: Grok 4.20 Non-Reasoning","created":1773100800,"description":"Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":2000000,"max_completion_tokens":2000000},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002"},"context_length":2000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"x-ai\/grok-4.20-reasoning","name":"SpaceXAI: Grok 4.20 Reasoning","created":1773100800,"description":"Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":2000000,"max_completion_tokens":2000000},"pricing":{"prompt":"0.00000125","completion":"0.0000025","input_cache_read":"0.0000002"},"context_length":2000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"openai\/gpt-5.4-fast","name":"OpenAI: GPT 5.4 (Fast)","created":1772668800,"description":"GPT-5.4 is OpenAI's best general-purpose model, part of the GPT-5 flagship model family. It's their most intelligent model yet for both general and agentic tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"pricing":{"prompt":"0.000005","completion":"0.00003","input_cache_read":"0.0000005"},"context_length":1050000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"id":"qwen\/qwen3.5-flash","name":"Qwen: Qwen 3.5 Flash","created":1771891200,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":64000},"pricing":{"prompt":"0.0000001","completion":"0.0000004","input_cache_read":"0.00000001","input_cache_write":"0.000000125"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}]}},{"id":"qwen\/qwen3.5-plus","name":"Qwen: Qwen 3.5 Plus","created":1771200000,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":64000},"pricing":{"prompt":"0.0000004","completion":"0.0000024","input_cache_read":"0.00000004","input_cache_write":"0.0000005"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}]}},{"id":"minimax\/minimax-m2.5-highspeed","name":"MiniMax: MiniMax M2.5 High Speed (retires Nov 18)","created":1770854400,"description":"M2.5 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":204800,"max_completion_tokens":131000},"pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"context_length":204800,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"expiration_date":"2026-11-18","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/gpt-5.3-codex-fast","name":"OpenAI: GPT 5.3 Codex (Fast)","created":1770249600,"description":"GPT-5.3-Codex advances both the frontier coding performance of GPT\u20115.2-Codex and the reasoning and professional knowledge capabilities of GPT\u20115.2, together in one model, which is also 25% faster. This enables it to take on long-running tasks that involve research, tool use, and complex execution.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000035","completion":"0.000028","input_cache_read":"0.00000035"},"context_length":400000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"id":"qwen\/qwen3-max-thinking","name":"Qwen: Qwen 3 Max Thinking","created":1769126400,"description":"Compared with the snapshot as of September 23, 2025, the Qwen-3 series Max model in this release achieves an effective integration of thinking and non-thinking modes, resulting in a comprehensive and substantial improvement in the model\u2019s overall performance. In thinking mode, the model simultaneously supports web search, web information extraction, and a code interpreter tool, enabling it to tackle more complex and challenging problems with greater accuracy by leveraging external tools while engaging in slow, deliberative reasoning. This version is based on a snapshot taken on January 23, 2026.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":256000,"max_completion_tokens":65536},"pricing":{"prompt":"0.0000012","completion":"0.000006","input_cache_read":"0.00000024"},"context_length":256000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"z-ai\/glm-4.7-flashx","name":"Z.ai: GLM 4.7 FlashX","created":1768780800,"description":" GLM-4.7-Flash balances high performance with efficiency, making it the perfect lightweight deployment option. ","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000006","completion":"0.0000004","input_cache_read":"0.00000001"},"context_length":200000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"minimax\/minimax-m2.1","name":"MiniMax: MiniMax M2.1","created":1766448000,"description":"MiniMax 2.1 is MiniMax's latest model, optimized specifically for robustness in coding, tool use, instruction following, and long-horizon planning.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":204800,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"context_length":204800,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["amazon-bedrock","minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"minimax\/minimax-m2.1-lightning","name":"MiniMax: MiniMax M2.1 Lightning (retires Nov 18)","created":1766448000,"description":"MiniMax-M2.1-lightning is a faster version of MiniMax-M2.1, offering the same performance but with significantly higher throughput (output speed ~100 TPS, MiniMax-M2 output speed ~60 TPS).","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":204800,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000003","completion":"0.0000024","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"context_length":204800,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"expiration_date":"2026-11-18","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"google\/gemini-3-flash","name":"Google: Gemini 3 Flash","created":1765929600,"description":"Google's most intelligent model built for speed, combining frontier intelligence with superior search and grounding.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65000},"pricing":{"prompt":"0.0000005","completion":"0.000003","input_cache_read":"0.00000005"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}]}},{"id":"openai\/gpt-5.2-fast","name":"OpenAI: GPT 5.2 (Fast)","created":1765411200,"description":"GPT-5.2 is OpenAI's best general-purpose model, part of the GPT-5 flagship model family. It's their most intelligent model yet for both general and agentic tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000035","completion":"0.000028","input_cache_read":"0.00000035"},"context_length":400000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"xhigh":{"reasoning":{"enabled":true,"effort":"xhigh"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}]}},{"id":"mistralai\/ministral-14b","name":"Mistral: Ministral 14B","created":1764633600,"description":"Ministral 3 14B is the largest model in the Ministral 3 family, offering state-of-the-art capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. Optimized for local deployment, it delivers high performance across diverse hardware, including local setups.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":256000},"pricing":{"prompt":"0.0000002","completion":"0.0000002","input_cache_read":"0.00000002"},"context_length":262144,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-oss-safeguard-120b","name":"OpenAI: GPT OSS Safeguard 120B","created":1764633600,"description":"GPT OSS Safeguard 120B is OpenAI\u2019s open-weight safety model for content moderation and guardrail enforcement. It helps teams evaluate content against custom safety policies and build scalable, adaptable protections for production AI applications.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":16000},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"context_length":128000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"deepseek\/deepseek-v3.2-thinking","name":"DeepSeek: DeepSeek V3.2 Thinking","created":1764547200,"description":"DeepSeek\u2011V3.2 from DeepSeek harmonizes high computational efficiency with superior reasoning and agent performance. It builds on three main techniques: DeepSeek Sparse Attention for long\u2011context efficiency, a scalable reinforcement learning framework, and a large\u2011scale agentic task synthesis pipeline. This model excels at long-context reasoning and agentic tasks, efficiently handling extended inputs while maintaining strong accuracy. Its sparse attention design enables it to process complex, multi-step workflows without excessive compute costs. Overall, DeepSeek\u2011V3.2 targets long\u2011context reasoning, tool\u2011using agents, and efficient deployment in production environments.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":8000},"pricing":{"prompt":"0.00000062","completion":"0.00000185"},"context_length":128000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["amazon-bedrock","deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"openai\/gpt-5.1-thinking","name":"OpenAI: GPT 5.1 Thinking","created":1762905600,"description":"An upgraded version of GPT-5 that adapts thinking time more precisely to the question to spend more time on complex questions and respond more quickly to simpler tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.000000125"},"context_length":400000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"openai\/gpt-5.1-thinking-fast","name":"OpenAI: GPT 5.1 Thinking (Fast)","created":1762905600,"description":"An upgraded version of GPT-5 that adapts thinking time more precisely to the question to spend more time on complex questions and respond more quickly to simpler tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000025","completion":"0.00002","input_cache_read":"0.00000025"},"context_length":400000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}]}},{"id":"nvidia\/nemotron-nano-12b-v2-vl","name":"NVIDIA: Nvidia Nemotron Nano 12B V2 VL","created":1761609600,"description":"The model is an auto-regressive vision language model that uses an optimized transformer architecture. The model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":131072},"pricing":{"prompt":"0.0000002","completion":"0.0000006"},"context_length":131072,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}]}},{"id":"minimax\/minimax-m2","name":"MiniMax: MiniMax M2 (retires Nov 18)","created":1761523200,"description":"MiniMax-M2 redefines efficiency for agents. It is a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":205000,"max_completion_tokens":205000},"pricing":{"prompt":"0.0000003","completion":"0.0000012","input_cache_read":"0.00000003","input_cache_write":"0.000000375"},"context_length":205000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"expiration_date":"2026-11-18","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":true,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]},"enkrypt":{"model_name":"minimax-m2","provider":"novita","source":"minimax","risk_score":17.6387,"bias_score":48.06,"cbrn_score":14,"harmful_score":10.56,"insecure_code_score":14.67,"toxicity_score":0.91,"robustness_score":null,"jailbreak_score":5.89928,"evasion_score":null,"safety_score":22.935,"nist_score":18,"owasp_score":21,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"interfaze\/interfaze-beta","name":"Interfaze Beta","created":1759795200,"description":"Interfaze is an AI model built on a new architecture that merges specialized DNN\/CNN models with LLMs for developer tasks that require deterministic output and high consistency like OCR, scraping, classification, STT and more.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":32000},"pricing":{"prompt":"0.0000015","completion":"0.0000035"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["interfaze"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"openai\/gpt-5-codex","name":"OpenAI: GPT-5-Codex","created":1757894400,"description":"GPT-5-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or similar environments.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000125","completion":"0.00001","input_cache_read":"0.00000013"},"context_length":400000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"qwen\/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","created":1757548800,"description":"Qwen3-Next uses a highly sparse MoE design: 80B total parameters, but only ~3B activated per inference step. Experiments show that, with global load balancing, increasing total expert parameters while keeping activated experts fixed steadily reduces training loss.Compared to Qwen3\u2019s MoE (128 total experts, 8 routed), Qwen3-Next expands to 512 total experts, combining 10 routed experts + 1 shared expert \u2014 maximizing resource usage without hurting performance. The Qwen3-Next-80B-A3B-Thinking excels at complex reasoning tasks \u2014 outperforming higher-cost models like Qwen3-30B-A3B-Thinking-2507 and Qwen3-32B-Thinking, outpeforming the closed-source Gemini-2.5-Flash-Thinking on multiple benchmarks, and approaching the performance of our top-tier model Qwen3-235B-A22B-Thinking-2507.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":262144},"pricing":{"prompt":"0.00000015","completion":"0.0000012"},"context_length":262144,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"nvidia\/nemotron-nano-9b-v2","name":"NVIDIA: Nvidia Nemotron Nano 9B V2","created":1755475200,"description":"NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.\\","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":131072},"pricing":{"prompt":"0.00000006","completion":"0.00000023"},"context_length":131072,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}]}},{"id":"openai\/gpt-5-fast","name":"OpenAI: GPT-5 (Fast)","created":1754524800,"description":"GPT-5 is OpenAI's flagship language model that excels at complex reasoning, broad real-world knowledge, code-intensive, and multi-step agentic tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.0000025","completion":"0.00002","input_cache_read":"0.00000025"},"context_length":400000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]}},{"id":"openai\/gpt-5-mini-fast","name":"OpenAI: GPT-5 mini (Fast)","created":1754524800,"description":"GPT-5 mini is a cost optimized model that excels at reasoning\/chat tasks. It offers an optimal balance between speed, cost, and capability.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"pricing":{"prompt":"0.00000045","completion":"0.0000036","input_cache_read":"0.000000045"},"context_length":400000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"minimal":{"reasoning":{"enabled":true,"effort":"minimal"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}]}},{"id":"openai\/gpt-4.1-mini-fast","name":"OpenAI: GPT-4.1 mini (Fast)","created":1747180800,"description":"GPT 4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive model for many use cases.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1047576,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000007","completion":"0.0000028","input_cache_read":"0.000000175"},"context_length":1047576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"qwen\/qwen-3-14b","name":"Qwen: Qwen3-14B","created":1745798400,"description":"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":40960,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000012","completion":"0.00000024"},"context_length":40960,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"instant":{"reasoning":{"enabled":false,"effort":"none"}},"thinking":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"toggle"}]}},{"id":"openai\/o3-fast","name":"OpenAI: o3 (Fast)","created":1744761600,"description":"OpenAI's o3 is their most powerful reasoning model, setting new state-of-the-art benchmarks in coding, math, science, and visual perception. It excels at complex queries requiring multi-faceted analysis, with particular strength in analyzing images, charts, and graphics.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":100000},"pricing":{"prompt":"0.0000035","completion":"0.000014","input_cache_read":"0.000000875"},"context_length":200000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]}},{"id":"openai\/o4-mini","name":"OpenAI: o4-mini","created":1744761600,"description":"OpenAI's o4-mini delivers fast, cost-efficient reasoning with exceptional performance for its size, particularly excelling in math (best-performing on AIME benchmarks), coding, and visual tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":100000},"pricing":{"prompt":"0.0000011","completion":"0.0000044","input_cache_read":"0.000000275"},"context_length":200000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]},"enkrypt":{"model_name":"o4-mini","provider":"openai","source":"OpenAI","risk_score":25.3367,"bias_score":79.84,"cbrn_score":12.67,"harmful_score":15,"insecure_code_score":12.44,"toxicity_score":6.73,"robustness_score":null,"jailbreak_score":5.39474,"evasion_score":null,"safety_score":24.4208,"nist_score":25,"owasp_score":30,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"openai\/gpt-4.1-fast","name":"OpenAI: GPT-4.1 (Fast)","created":1744588800,"description":"GPT 4.1 is OpenAI's flagship model for complex tasks. It is well suited for problem solving across domains.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1047576,"max_completion_tokens":32768},"pricing":{"prompt":"0.0000035","completion":"0.000014","input_cache_read":"0.000000875"},"context_length":1047576,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"openai\/o3-mini","name":"OpenAI: o3-mini","created":1738281600,"description":"o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini.","architecture":{"input_modalities":["text","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":100000},"pricing":{"prompt":"0.0000011","completion":"0.0000044","input_cache_read":"0.00000055"},"context_length":200000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]},"enkrypt":{"model_name":"o3-mini","provider":"OpenAI","source":"OpenAI","risk_score":25.4653,"bias_score":81.91,"cbrn_score":8.33,"harmful_score":15.56,"insecure_code_score":16.89,"toxicity_score":4.64,"robustness_score":null,"jailbreak_score":4.07895,"evasion_score":null,"safety_score":22.8282,"nist_score":25,"owasp_score":30,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"deepseek\/deepseek-r1","name":"DeepSeek: DeepSeek-R1","created":1737331200,"description":"DeepSeek-R1 provides customers a state-of-the-art reasoning model, optimized for general reasoning tasks, math, science, and code generation.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000135","completion":"0.0000054"},"context_length":128000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning"],"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"variants":{"none":{"reasoning":{"enabled":false,"effort":"none"}},"low":{"reasoning":{"enabled":true,"effort":"low"}},"high":{"reasoning":{"enabled":true,"effort":"high"}},"max":{"reasoning":{"enabled":true,"effort":"max"}}},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}]}},{"id":"openai\/o1","name":"OpenAI: o1 ($$$$)","created":1733356800,"description":"o1 is OpenAI's flagship reasoning model, designed for complex problems that require deep thinking. It provides strong reasoning capabilities with improved accuracy for complex multi-step tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":200000,"max_completion_tokens":100000},"pricing":{"prompt":"0.000015","completion":"0.00006","input_cache_read":"0.0000075"},"context_length":200000,"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai","variants":{"low":{"reasoning":{"enabled":true,"effort":"low"}},"medium":{"reasoning":{"enabled":true,"effort":"medium"}},"high":{"reasoning":{"enabled":true,"effort":"high"}}},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]},"enkrypt":{"model_name":"o1","provider":"openai","source":"OpenAI","risk_score":20.6856,"bias_score":82.17,"cbrn_score":3.67,"harmful_score":3.89,"insecure_code_score":11.11,"toxicity_score":2.59,"robustness_score":null,"jailbreak_score":0.921053,"evasion_score":null,"safety_score":20.029,"nist_score":21,"owasp_score":26,"ingestedAt":"2026-09-04T04:01:19.650Z","evaluatedAt":null,"lastCheckedAt":"2026-11-11T04:00:23.964Z","staleAfter":"2026-11-12T06:00:23.964Z","freshness":"stale"}},{"id":"amazon\/nova-lite","name":"Amazon: Nova Lite","created":1733184000,"description":"A very low cost multimodal model that is lightning fast for processing image, video, and text inputs.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":300000,"max_completion_tokens":8192},"pricing":{"prompt":"0.00000006","completion":"0.00000024","input_cache_read":"0.000000015"},"context_length":300000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"amazon\/nova-micro","name":"Amazon: Nova Micro","created":1733184000,"description":"A text-only model that delivers the lowest latency responses at very low cost.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":8192},"pricing":{"prompt":"0.000000035","completion":"0.00000014","input_cache_read":"0.0000000087"},"context_length":128000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"amazon\/nova-pro","name":"Amazon: Nova Pro","created":1733184000,"description":"A highly capable multimodal model with the best combination of accuracy, speed, and cost for a wide range of tasks.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":300000,"max_completion_tokens":8192},"pricing":{"prompt":"0.0000008","completion":"0.0000032","input_cache_read":"0.0000002"},"context_length":300000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/ministral-3b","name":"Mistral: Ministral 3B","created":1729036800,"description":"A compact, efficient model for on-device tasks like smart assistants and local analytics, offering low-latency performance.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":4000},"pricing":{"prompt":"0.0000001","completion":"0.0000001","input_cache_read":"0.00000001"},"context_length":131072,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice"],"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/ministral-8b","name":"Mistral: Ministral 8B","created":1729036800,"description":"A more powerful model with faster, memory-efficient inference, ideal for complex workflows and demanding edge applications.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":4000},"pricing":{"prompt":"0.00000015","completion":"0.00000015","input_cache_read":"0.000000015"},"context_length":262144,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"mistralai\/mistral-small","name":"Mistral: Mistral Small","created":1726531200,"description":"Mistral Small currently runs Mistral Small 4, a multimodal model combining instruction following, reasoning, and coding with a 262,144-token context window.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":4000},"pricing":{"prompt":"0.00000015","completion":"0.0000006","input_cache_read":"0.000000015"},"context_length":262144,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-4o-mini-fast","name":"OpenAI: GPT-4o mini (Fast)","created":1721260800,"description":"GPT-4o mini from OpenAI is their most advanced and cost-efficient small model. It is multi-modal (accepting text or image inputs and outputting text) and has higher intelligence than gpt-3.5-turbo but is just as fast.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000025","completion":"0.000001","input_cache_read":"0.000000125"},"context_length":128000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"mistralai\/codestral","name":"Mistral: Mistral Codestral","created":1716940800,"description":"Mistral's cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.","architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":4000},"pricing":{"prompt":"0.0000003","completion":"0.0000009","input_cache_read":"0.00000003"},"context_length":128000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{}},{"id":"openai\/gpt-4o-fast","name":"OpenAI: GPT-4o (Fast)","created":1715558400,"description":"GPT-4o from OpenAI has broad general knowledge and domain expertise allowing it to follow complex instructions in natural language and solve difficult problems accurately. It matches GPT-4 Turbo performance with a faster and cheaper API.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":16384},"pricing":{"prompt":"0.00000425","completion":"0.000017","input_cache_read":"0.000002125"},"context_length":128000,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","response_format","structured_outputs"],"inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"opencode":{"ai_sdk_provider":"openai"}},{"id":"kilo-auto\/frontier","name":"Auto Frontier","created":0,"description":"Highest performance and capability for any task.","architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"pricing":{"prompt":"-1","completion":"-1","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"opencode":{},"inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"autoRouting":{"models":["anthropic\/claude-fable-5.2","anthropic\/claude-opus-5.5","anthropic\/claude-sonnet-5.5","google\/gemini-4-argon","google\/gemini-4-carbon","meta\/muse-wonder","moonshotai\/kimi-k3","moonshotai\/kimi-k3.1-pro","openai\/gpt-6-astra","openai\/gpt-6.1-sol","openai\/gpt-6.1-terra","x-ai\/grok-4.7"]}},{"id":"kilo-auto\/balanced","name":"Auto Balanced","created":0,"description":"Great balance of price and capability.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":65536},"pricing":{"prompt":"-1","completion":"-1","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"context_length":1000000,"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"opencode":{},"inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"autoRouting":{"models":["anthropic\/claude-haiku-5.5","deepseek\/deepseek-v4.1-flash-1017","google\/gemini-3.8-flash","inclusionai\/ling-3.1-flash","mistralai\/mistral-large-4-0","moonshotai\/kimi-k3","openai\/gpt-6-luna","qwen\/qwen3.8-flash","qwen\/qwen3.8-max-0902","stepfun\/step-5-preview","x-ai\/grok-4.7","xiaomi\/mimo-v2.6-pro","z-ai\/glm-5.3","z-ai\/glm-5.3-flash"]}},{"id":"kilo-auto\/small","name":"Auto Small","created":0,"description":"Automatically routes your request to a small model.","architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":32768},"pricing":{"prompt":"0.00000005","completion":"0.0000004","input_cache_read":"0.000000005","request":"0","image":"0","web_search":"0","internal_reasoning":"0"},"context_length":262144,"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"opencode":{},"inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"autoRouting":{"models":["google\/gemma-4-26b-a4b-it"]}}]}