(Some) current model API names
Curated model identifiers and their key capabilities (not a complete historical list).
⌘K
OpenAI Models
Reasoning Effort Levels
Supports reasoning.effort parameter:
low, medium (default), high, and
extra-high (xhigh) for Codex 5.1.
GPT-5 Series (Reasoning)
| Model Name | API Identifier | Context | Max Output |
|---|---|---|---|
| GPT-5.1 | gpt-5.1 | 400,000 | 128,000 |
| GPT-5 Pro | gpt-5-pro | 400,000 | 128,000 |
| GPT-5 | gpt-5 | 400,000 | 128,000 |
| GPT-5 mini | gpt-5-mini | 200,000 | 64,000 |
GPT-5 Codex (Coding)
| Model Name | API Identifier | Context | Max Output |
|---|---|---|---|
| GPT-5.1 Codex | gpt-5.1-codex | 400,000 | 128,000 |
| GPT-5.1 Codex Max | gpt-5.1-codex-max | 400,000 | |
| GPT-5.1 Codex Mini | gpt-5.1-codex-mini | 400,000 | 100,000 |
O-Series (Reasoning)
| Model Name | API Identifier | Context | Max Output |
|---|---|---|---|
| o3-deep-research | o3-deep-research | 200k | 100k |
| o3 / o3-pro | o3 / o3-pro | 200k | 100k |
| o3-mini / o4-mini | o3-mini / o4-mini | 200k | 100k |
| o1 / o1-pro | o1 / o1-pro | 200k | 100k |
Google Gemini
Thinking Mode: Binary on/off switch for Gemini 3 and 2.5 series.
Gemini 3 Series
| Model Name | API Identifier | Context | Thinking |
|---|---|---|---|
| Gemini 3 Pro | gemini-3-pro-preview | 1M+ | Yes |
| Gemini 3 Pro Image | gemini-3-pro-image-preview | 1M+ | Yes |
Gemini 2.5 Series
| Model Name | API Identifier | Context |
|---|---|---|
| Gemini 2.5 Pro | gemini-2.5-pro | 1M+ |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M+ |
Anthropic Claude
Claude 4.5
Extended Thinking Available
| Model Name | API Identifier |
|---|---|
| Sonnet 4.5 | claude-sonnet-4-5 |
| Haiku 4.5 | claude-haiku-4-5 |
Claude 4.1
Extended Thinking Available
| Model Name | API Identifier |
|---|---|
| Opus 4.1 | claude-opus-4-1 |
| Snapshot | claude-opus-4-1-20250805 |
Meta Llama
Llama 4 Series (Multimodal)
| Model Name | API Identifier | Capabilities |
|---|---|---|
| Llama 4 Maverick | Llama-4-Maverick-17B-128E-Instruct-FP8 | Text, Image |
| Llama 4 Scout | Llama-4-Scout-17B-16E-Instruct-FP8 | Text, Image |
Mistral AI
Magistral Series (Reasoning)
| Model Name | API Identifier | Reasoning |
|---|---|---|
| Magistral Medium 1.2 | magistral-medium-2509 | Yes |
| Magistral Small 1.2 | magistral-small-2509 | Yes |
Edge / Specialist
Ministral 3B
ministral-3b-2410 Ministral 8B
ministral-8b-2410 Codestral
codestral OCR
mistral-ocr-2505 xAI Grok
Grok 4.1 & 4 Series
| Model Name | API Identifier | Context | Reasoning |
|---|---|---|---|
| Grok 4.1 Fast Reasoning | grok-4-1-fast-reasoning | 2M | Yes |
| Grok 4.1 Fast Non-Reasoning | grok-4-1-fast-non-reasoning | 2M | No |
| Grok 4 Fast Reasoning | grok-4-fast-reasoning | 2M | Yes |
DeepSeek
| Model Name | API Identifier |
|---|---|
| R1 (Reasoning) | deepseek-r1 |
| V3 (General) | deepseek-v3 |
| V3.1 Terminus | deepseek-v3.1-terminus |
Cohere
| Model Name | API Identifier |
|---|---|
| Command A Reasoning | command-a-reasoning-08-2025 |
| Command A | command-a-03-2025 |
| Command R7B | command-r7b-12-2024 |
Note
This is a living list of current APIs we track. It is not an exhaustive historical catalog.