# Cursor Documentation Cursor is a coding agent for building ambitious software. Use it to understand your codebase, plan and build features, fix bugs, review changes, and work with the tools you already use. ![Welcome to Cursor, the AI editor and coding agent](/docs-static/images/agent/homepage-hero.png) ## Start here ### Get started Go from install to your first useful change in Cursor ### Models & Pricing Compare models, usage pools, and plan pricing ### Changelog Stay up to date with the latest features and improvements ## What you can do with Cursor ### Understand your code Trace how a repo fits together and find the right places to start ### Plan and build features Scope changes, use Plan Mode, and ship bigger work with confidence ### Find and fix bugs Reproduce issues, narrow the root cause, and verify the fix ### Review changes Inspect diffs, run checks, and catch problems before you merge ### Customize Cursor Add plugins, skills, MCPs, and rules from one place ### Connect your workflow Work with GitHub, GitLab, Azure DevOps, Bitbucket, JetBrains, Slack, Linear, and more ## Models See all model attributes on the [Models & Pricing](https://cursor.com/docs/models-and-pricing.md) page. | Model | Provider | Default context | Max context | Capabilities | Notes | | --------------------------------------------------------------------------------------------------------------------------- | --------- | --------------- | ----------- | ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Claude 4 Sonnet](https://www.anthropic.com/claude/sonnet) | Anthropic | 200k | - | Agent, Thinking, Images | Hidden by default; Thinking variant counts as 2 requests in legacy pricing | | [Claude 4 Sonnet 1M](https://www.anthropic.com/claude/sonnet) | Anthropic | - | 1M | Agent, Thinking, Images | Hidden by default; Thinking variant counts as 2 requests in legacy pricing; This model can be very expensive due to the large context window; The cost is 2x when the input exceeds 200k tokens | | [Claude 4.5 Haiku](https://www.anthropic.com/claude/haiku) | Anthropic | 200k | - | Thinking, Images | Hidden by default; Bedrock/Vertex: regional endpoints +10% surcharge; Cache: writes 1.25x, reads 0.1x | | [Claude 4.5 Opus](https://www.anthropic.com/claude/opus) | Anthropic | 200k | 200k | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans | | [Claude 4.5 Sonnet](https://www.anthropic.com/claude/sonnet) | Anthropic | 200k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) | | [Claude 4.6 Opus](https://www.anthropic.com/claude/opus) | Anthropic | 200k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) | | [Claude 4.6 Sonnet](https://www.anthropic.com/claude/sonnet) | Anthropic | 200k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) | | [Claude 4.7 Opus](https://www.anthropic.com/claude/opus) | Anthropic | 300k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) | | [Claude Fable 5](https://www.anthropic.com/claude/fable) | Anthropic | 300k | 1M | Agent, Thinking, Images | Hidden by default; Requires data retention approval for Enterprise customers, Teams and individual customers with Privacy Mode enabled; Anthropic stores agent input and output data for harm-prevention processes; this data is not used to train or improve Anthropic models or products; Requests that trip a security guardrail are automatically routed to Claude Opus; About 2x the cost of Claude Opus 5; Requires Max Mode on legacy request-based plans | | [Claude Fable 5.1](https://www.anthropic.com/claude/fable) | Anthropic | 300k | 1M | Agent, Thinking, Images | Hidden by default; Requires data retention approval for Enterprise customers, Teams and individual customers with Privacy Mode enabled; Anthropic stores agent input and output data for harm-prevention processes; this data is not used to train or improve Anthropic models or products; Requests that trip a security guardrail are automatically routed to Claude Opus; Prompt-cache reads are $0.25/M, 75% below the standard cache-read rate; About 2.5x the cost of Claude Opus 5.5 on input and output; Requires Max Mode on legacy request-based plans | | [Claude Fable 5.2](https://www.anthropic.com/claude/fable) | Anthropic | 300k | 1M | Agent, Thinking, Images | Requires data retention approval for Enterprise customers, Teams and individual customers with Privacy Mode enabled; Anthropic stores agent input and output data for harm-prevention processes; this data is not used to train or improve Anthropic models or products; Requests that trip a security guardrail are automatically routed to Claude Opus; 20% cheaper than Claude Fable 5.1 on input and output; About 2x the cost of Claude Opus 5.5 on input and output; Requires Max Mode on legacy request-based plans | | [Claude Haiku 5.5](https://www.anthropic.com/claude/haiku) | Anthropic | 300k | 1M | Agent, Thinking, Images | Requires Max Mode on legacy request-based plans; Requests above 100k input tokens bill at 5x the standard rates ($0.50/M input, $0.625/M cache write, $0.05/M cache read, $2.50/M output); 90% cheaper than Claude 4.5 Haiku on input and output for requests up to 100k input tokens | | [Claude Opus 4.7 (fast mode)](https://www.anthropic.com/claude/opus) | Anthropic | 200k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Limited research preview; Up to 1M tokens with extended context at the same per-token rates as shorter context | | [Claude Opus 4.8](https://www.anthropic.com/claude/opus) | Anthropic | 300k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Fast mode (\`claude-opus-4-8-fast\`) requires Max Mode on legacy request-based plans; Fast mode is 3x lower per-token pricing than Opus 4.7 fast mode; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) | | [Claude Opus 5](https://www.anthropic.com/claude/opus) | Anthropic | 300k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Fast mode (\`claude-opus-5-fast\`) requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) | | [Claude Opus 5.5](https://www.anthropic.com/claude/opus) | Anthropic | 300k | 1M | Agent, Thinking, Images | Requires Max Mode on legacy request-based plans; Fast mode (\`claude-opus-5-5-fast\`) requires Max Mode on legacy request-based plans; 20% cheaper than Claude Opus 5 on input and output; Prompt-cache reads are $0.20/M (0.05x input), down from 0.10x input on Claude Opus 5; Regional and US-only endpoints are priced 10% higher ($4.40/M input, $22/M output); Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) | | [Claude Sonnet 5](https://www.anthropic.com/claude/sonnet) | Anthropic | 200k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge); Uses an updated tokenizer, so the same input can map to more tokens | | [Claude Sonnet 5.5](https://www.anthropic.com/claude/sonnet) | Anthropic | 200k | 1M | Agent, Thinking, Images | Requires Max Mode on legacy request-based plans; Same input and output rates as Claude Sonnet 5, with cache reads at $0.10/M instead of $0.20/M; US-only endpoints are priced 10% higher ($2.20/M input, $11/M output); Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge) | | [Composer 1](https://cursor.com) | Cursor | 200k | - | Agent, Images | Hidden by default | | [Composer 2.5](https://cursor.com/blog/composer-2-5) | Cursor | 200k | - | Agent, Thinking, Images | - | | [DeepSeek V4.1 Flash 1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017) | DeepSeek | 1M | - | Agent, Thinking | Hidden by default | | [Gemini 2.5 Flash](https://developers.googleblog.com/en/start-building-with-gemini-25-flash/) | Google | 200k | 1M | Agent, Thinking, Images | Hidden by default | | [Gemini 3 Flash](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Agent, Thinking, Images | Hidden by default | | [Gemini 3 Pro](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Agent, Thinking, Images | Hidden by default | | [Gemini 3 Pro Image Preview](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Images | Hidden by default; Native image generation model optimized for speed, flexibility, and contextual understanding; Text input and output priced the same as Gemini 3 Pro; Image output: $120/1M tokens (\~$0.134 per 1K/2K image, \~$0.24 per 4K image); Preview models may change before becoming stable and have more restrictive rate limits | | [Gemini 3.1 Pro](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Agent, Thinking, Images | - | | [Gemini 3.5 Flash](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Agent, Thinking, Images | Hidden by default | | [Gemini 3.5 Flash Lite](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite) | Google | - | - | - | Hidden by default; Used only for the Auto-review classifier. It is not selectable as a chat or agent model | | [Gemini 3.6 Flash](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Agent, Thinking, Images | Hidden by default | | [Gemini 3.7 Flash](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Agent, Thinking, Images | Hidden by default | | [Gemini 3.8 Flash](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Agent, Thinking, Images | - | | [Gemini 4 Argon](https://ai.google.dev/gemini-api/docs) | Google | 200k | 1M | Agent, Thinking, Images | - | | [Gemini 4 Carbon](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/) | Google | 200k | 1M | Agent, Thinking, Images | Introductory pricing through November 30, 2026. From December 1, 2026: $4 input, $0.20 cache read, $20 output per 1M tokens | | [Gemini 4 Hydrogen](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/) | Google | 200k | 1M | Agent, Thinking, Images | - | | [GLM 5.2](https://z.ai) | Z.ai | 200k | - | Agent, Thinking | Hidden by default | | [GLM 5.3](https://z.ai) | Z.ai | 1M | - | Agent, Thinking | Hidden by default; Same per-token rates as GLM 5.2 | | [GLM 5.3 Flash](https://z.ai) | Z.ai | 1M | - | Agent, Thinking, Images | Hidden by default | | [GPT-5](https://openai.com/index/gpt-5/) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Agentic and reasoning capabilities; Available reasoning effort variant is gpt-5-high | | [GPT-5 Fast](https://openai.com/index/gpt-5/) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Faster speed but 2x price; Available reasoning effort variants are gpt-5-high-fast, gpt-5-low-fast | | [GPT-5 Mini](https://openai.com/index/gpt-5/) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default | | [GPT-5-Codex](https://platform.openai.com/docs/models/gpt-5-codex) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Agentic and reasoning capabilities | | [GPT-5.1 Codex](https://platform.openai.com/docs/models/gpt-5-codex) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Agentic and reasoning capabilities | | [GPT-5.1 Codex Max](https://platform.openai.com/docs/models/gpt-5-codex) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default | | [GPT-5.1 Codex Mini](https://platform.openai.com/docs/models/gpt-5-codex) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Agentic and reasoning capabilities; 4x rate limits compared to GPT-5.1 Codex | | [GPT-5.2](https://openai.com/index/gpt-5/) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Agentic and reasoning capabilities; Available reasoning effort variant is gpt-5.2-high | | [GPT-5.2 Codex](https://platform.openai.com/docs/models/gpt-5-codex) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Agentic and reasoning capabilities | | [GPT-5.3 Codex](https://platform.openai.com/docs/models/gpt-5-codex) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Agentic and reasoning capabilities; Available reasoning effort variant is gpt-5.3-codex-high | | [GPT-5.4](https://developers.openai.com/api/docs/models/gpt-5.4) | OpenAI | 272k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Agentic and reasoning capabilities; 90% discount on cached input tokens; Fast mode is 15% faster with 2x pricing; Long context supports up to 1M tokens with 2x input pricing | | [GPT-5.4 Mini](https://developers.openai.com/api/docs/models/gpt-5.4-mini) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Smaller, faster variant of GPT-5.4; 90% discount on cached input tokens | | [GPT-5.4 Nano](https://developers.openai.com/api/docs/models/gpt-5.4-nano) | OpenAI | 272k | - | Agent, Thinking, Images | Hidden by default; Smallest GPT-5.4 variant, optimized for cost; 90% discount on cached input tokens | | [GPT-5.5](https://developers.openai.com/api/docs/models/gpt-5.5) | OpenAI | 272k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Agentic and reasoning capabilities; More token-efficient than GPT-5.4 on comparable tasks; Improved persistence on long-running tasks; Fast mode is available at higher rates; Long context supports up to 1M tokens with 2x input pricing | | [GPT-5.6 Luna](https://openai.com/index/previewing-gpt-5-6-sol/) | OpenAI | 272k | 1M | Agent, Thinking, Images | Requires Max Mode on legacy request-based plans; Smallest GPT-5.6 variant, optimized for cost and speed; Agentic and reasoning capabilities; Fast mode is available at 2x pricing; Long context supports up to 1M tokens with 2x input pricing; Fast mode is available for long context (>272k) at 2x Fast input pricing; Cache writes are billed at 1.25x the uncached input rate | | [GPT-5.6 Sol](https://openai.com/index/previewing-gpt-5-6-sol/) | OpenAI | 272k | 1M | Agent, Thinking, Images | Requires Max Mode on legacy request-based plans; Agentic and reasoning capabilities; Fast mode is available at 2x pricing; Long context supports up to 1M tokens with 2x input pricing; Fast mode is available for long context (>272k) at 2x Fast input pricing; Cache writes are billed at 1.25x the uncached input rate; Promotional pricing through November 21, 2026 | | [GPT-5.6 Terra](https://openai.com/index/previewing-gpt-5-6-sol/) | OpenAI | 272k | 1M | Agent, Thinking, Images | Requires Max Mode on legacy request-based plans; Mid-tier GPT-5.6 variant between Sol and Luna; Agentic and reasoning capabilities; Fast mode is available at 2x pricing; Long context supports up to 1M tokens with 2x input pricing; Fast mode is available for long context (>272k) at 2x Fast input pricing; Cache writes are billed at 1.25x the uncached input rate | | Grok 4.5 | Cursor | 256k | - | Agent, Thinking | Jointly trained by Cursor and SpaceXAI | | Grok 4.6 | Cursor | 256k | - | Agent, Thinking | Jointly trained by Cursor and SpaceXAI | | [Grok 4.7](https://x.ai/news/grok-4-7) | Cursor | 256k | 500k | Agent, Thinking | Jointly trained by Cursor and SpaceXAI; Long context (>256k input tokens) is billed at 2x standard rates, up to 500k; Fast mode is available at 2x pricing; Fast mode for long context (>256k) is billed at 3x standard rates | | Kimi K2.7 Code | Moonshot | 262k | - | Agent, Thinking, Images | Hidden by default | | [Kimi K3](https://www.moonshot.ai) | Moonshot | 200k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge); No separate cache-write fee | | [Muse Spark 1.3](https://dev.meta.ai/docs/models) | Meta | 300k | 1M | Agent, Thinking, Images | Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens in Max Mode at the same per-token rates (no long-context surcharge); Cached input is billed at $0.15 per million tokens with no separate cache-write charge | | [Muse Wonder](https://dev.meta.ai/docs/models) | Meta | 300k | 1M | Agent, Thinking, Images | Up to 1M tokens in Max Mode at the same per-token rates (no long-context surcharge); Cached input is billed at $0.20 per million tokens with no separate cache-write charge | ## More resources ### Downloads Get Cursor for your computer ### Help Find answers to common questions and troubleshooting guides For account and billing questions, contact our support team --- ## Sitemap [Overview of all docs pages](/llms.txt)