《Cursor Docs》-Muse Wonder
Teams and Enterprise admins who configured model access before Meta was available need to enable the Meta provider before Muse Wonder appears for their members.
Read More《Cursor Docs》-Grok 4 7
Grok 4.7 is a frontier model from Cursor and SpaceXAI for coding and knowledge work. It builds on Grok 4.6 with a larger base, longer training on harder multi hour tasks, and stronger self verification.
Read More《Cursor Docs》-Glm 5 3 Flash
GLM 5.3 Flash is the smaller, faster member of Z.ai's GLM 5.3 family. It supports image inputs, a 1M token context window, and three reasoning levels (Low, High, and Max), with High as the default. Add it to the model picker from Cursor Settings Models . For higher quality on harder tasks, use GLM 5.3.
Read More《Cursor Docs》-Glm 5 3
GLM 5.3 is Z.ai's latest open weight coding model and the successor to GLM 5.2. It supports a 1M token context window and three reasoning levels (Low, High, and Max), with High as the default. Add it to the model picker from Cursor Settings Models . For a faster, lower cost option from the same family, see GLM 5.3 Flash.
Read More《Cursor Docs》-Gemini 4 Argon
Gemini 4 Argon is Google's frontier Gemini model. Use it for complex, multi step coding work that benefits from deeper reasoning and a large context window.
Read More《Cursor Docs》-Gemini 3 5 Flash Lite
This model is used only by the Auto review classifier inside Cursor. It isn't selectable as a chat or agent model.
Read More《Cursor Docs》-Claude Sonnet 5 5
Claude Sonnet 5.5 is Anthropic's latest medium tier model and the successor to Sonnet 5. It scores 55.5% on CursorBench at max effort, second only to Opus 5.5. It keeps Sonnet 5's input and output rates and halves the cache read rate. Add it to the model picker from Cursor Settings Models .
Read More《Cursor Docs》-Claude Opus 5 5
Claude Opus 5.5 is Anthropic's latest Opus model and replaces Opus 5. It sets a new high score on CursorBench, ahead of Fable 5.1, and costs 20% less than Opus 5 per token. We recommend the high thinking variant for the best results.
Read More《Cursor Docs》-Claude Haiku 5 5
Claude Haiku 5.5 is the fastest model in Anthropic's Claude 5.5 family and the successor to Claude 4.5 Haiku. It scores 48.4% on CursorBench at max effort, on the same cost performance curve as Sonnet 5.5 and Opus 5.5, at a tenth of Haiku 4.5's per token price for requests up to 100k input tokens. Add it to the model picker from Cursor Settings Models .
Read More《Cursor Docs》-Muse Spark 1 3
Meta is a new model provider in Cursor. Teams and Enterprise admins who configured model access before Meta was available need to enable the Meta provider before Muse Spark 1.3 appears for their members.
Read More《Cursor Docs》-Kimi K3
Kimi K3 is Moonshot AI's latest open weight model. It sits above Kimi K2.7 Code for long running agent work: thorough upfront reasoning, strong one shot persistence, and the highest CursorBench score we've measured from an open model.
Read More《Cursor Docs》-Kimi K2 7 Code
We recommend using Kimi K3 for new work. K2.7 Code remains available as a lower cost Moonshot option.
Read More《Cursor Docs》-Grok 4 6
Grok 4.6 is a frontier model from Cursor and SpaceXAI for complex coding and knowledge work. It builds on Grok 4.5 with improved instruction following and long horizon agentic work.
Read More《Cursor Docs》-Grok 4 5
We recommend using Grok 4.6 for improved instruction following and long horizon agentic work. Grok 4.5 remains available.
Read More《Cursor Docs》-Gpt 5 Mini
We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.
Read More《Cursor Docs》-Gpt 5 Fast
We recommend using GPT 5.3 Codex. It's faster than previous generations and more cost effective.
Read More《Cursor Docs》-Gpt 5 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 6 Terra
GPT 5.6 Terra is the mid tier model in OpenAI's GPT 5.6 family. It sits between Sol and Luna on intelligence and price, making it a strong pick for everyday agentic coding when you want more capability than Luna without Sol's cost.
Read More《Cursor Docs》-Gpt 5 6 Sol
GPT 5.6 Sol is OpenAI's flagship GPT 5.6 model in Cursor. It is the strongest of the Sol, Terra, and Luna family: persistent on long running agent work, fast enough for interactive sessions, and notably concise in how it communicates.
Read More《Cursor Docs》-Gpt 5 6 Luna
GPT 5.6 Luna is the smallest and lowest cost model in OpenAI's GPT 5.6 family. Use it for high volume, latency sensitive, or cost sensitive agent work where Sol or Terra would be more than you need.
Read More《Cursor Docs》-Gpt 5 5
GPT 5.5 is OpenAI's most intelligent model in Cursor. It keeps momentum on long running work and stays on task for significantly longer before stopping early, which matters most in complex, multi step coding sessions.
Read More《Cursor Docs》-Gpt 5 4 Nano
GPT 5.4 Nano is the smallest and fastest model in the GPT 5.4 family. At $0.20 per million input tokens, it's built for high volume workloads where speed and cost matter more than peak reasoning. Reach for it when you need quick classification, extraction, ranking, or lightweight coding support.
Read More《Cursor Docs》-Gpt 5 4 Mini
GPT 5.4 Mini brings good performance to cost sensitive workflows.
Read More《Cursor Docs》-Gpt 5 4
GPT 5.4 is OpenAI's most capable model to date. It outperforms all other models on our internal benchmarks. For cost sensitive workflows where raw intelligence matters less, GPT 5.3 Codex remains a strong option at a lower price point.
Read More《Cursor Docs》-Gpt 5 3 Codex
GPT 5.3 Codex is OpenAI's flagship coding model. It leads Terminal Bench by a wide margin and performs on par with Opus 4.6 on our internal benchmarks, at roughly one third the price. Much faster than previous GPT generations. A strong default for most coding tasks.
Read More《Cursor Docs》-Gpt 5 2 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 2
GPT 5.2 has access to all agent tools when used with Cursor including:
Read More《Cursor Docs》-Gpt 5 1 Codex Mini
We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.
Read More《Cursor Docs》-Gpt 5 1 Codex Max
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 1 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5
We recommend using GPT 5.3 Codex. It scores higher on benchmarks, is faster, and more cost effective.
Read More《Cursor Docs》-Glm 5 2
GLM 5.2 has access to all agent tools when used with Cursor including:
Read More《Cursor Docs》-Gemini 3 Pro Image Preview
This model is used exclusively for the image generation tool inside Cursor. It is not selectable as a chat model.
Read More《Cursor Docs》-Gemini 3 Pro
We recommend using Gemini 3.1 Pro. It's the latest version with stronger multimodal capabilities and the same pricing.
Read More《Cursor Docs》-Gemini 3 Flash
Gemini 3 Flash is Google's speed optimized model. At $0.50 per million input tokens, it's one of the cheapest options available. Use it for simple coding tasks, quick edits, and executing plans written by a more capable model.
Read More《Cursor Docs》-Gemini 3 8 Flash
Gemini 3.8 Flash is Google's latest speed tier model. It pairs strong agentic coding performance with low per token costs. Use it for high throughput coding tasks that benefit from reasoning and a large context window.
Read More《Cursor Docs》-Gemini 3 7 Flash
We recommend using Gemini 3.8 Flash. It's Google's latest speed tier model at the same price.
Read More《Cursor Docs》-Gemini 3 6 Flash
We recommend using Gemini 3.8 Flash. It's Google's latest speed tier model with lower input and output prices.
Read More《Cursor Docs》-Gemini 3 5 Flash
We recommend using Gemini 3.8 Flash. It's Google's latest speed tier model with lower input and output prices.
Read More《Cursor Docs》-Gemini 3 1 Pro
Gemini 3.1 Pro is Google's latest model. It processes images alongside code, making it strong for UI/UX work from design mockups. It supports context windows up to 1M tokens.
Read More《Cursor Docs》-Gemini 2 5 Flash
We recommend using Gemini 3.8 Flash. It's Google's latest speed tier model.
Read More《Cursor Docs》-Cursor Composer 2 5
Composer 2.5 is Cursor's own agentic model. It builds on Composer 2 with stronger intelligence on long agentic tasks, better effort calibration, tool selection, intent understanding, and reliability.
Read More《Cursor Docs》-Cursor Composer 1
We strongly recommend using Composer 2.5. It's smarter and includes more usage on individual plans.
Read More《Cursor Docs》-Claude Sonnet 5
Claude Sonnet 5 is Anthropic's latest medium tier model and replaces Sonnet 4.6. It pushes quality close to Opus while keeping Sonnet's lower per token price. It supports thinking mode and context windows up to 1M tokens, making it a strong default for everyday coding when you want frontier reasoning without Opus pricing.
Read More《Cursor Docs》-Claude Opus 5
Claude Opus 5 is Anthropic's latest Opus model and replaces Opus 4.8. It is a step change over Opus 4.8 on agentic coding, professional knowledge work, and long horizon reasoning, and it lands on par with Fable 5 on CursorBench at Opus pricing. We recommend the high thinking variant for the best results.
Read More《Cursor Docs》-Claude Opus 4 8
We recommend using Claude Opus 5. It replaces Opus 4.8 with stronger agentic coding and long horizon reasoning at the same price.
Read More《Cursor Docs》-Claude Opus 4 7 Fast
Fast mode for Claude Opus 4.7 bills at a much higher per token rate than standard Opus 4.7. Use it selectively for time sensitive or critical work where cost is secondary.
Read More《Cursor Docs》-Claude Opus 4 7
We recommend using Claude Opus 5. It is Anthropic's latest Opus release with the same pricing and stronger agentic capabilities.
Read More《Cursor Docs》-Claude Opus 4 6
We recommend using Claude Opus 5. It scores higher on CursorBench, offers stronger autonomous capabilities, and is priced the same.
Read More《Cursor Docs》-Claude Opus 4 5
We recommend using Claude Opus 5. It's the latest Opus with stronger reasoning and code quality.
Read More《Cursor Docs》-Claude Fable 5 1
Claude Fable 5.1 is Anthropic's latest Mythos class model and replaces Fable 5. It is built for long running, complex, and asynchronous coding and knowledge work. Input and output rates match Fable 5. Prompt cache reads are 75% cheaper.
Read More《Cursor Docs》-Claude Fable 5
We recommend using Claude Fable 5.1. It is Anthropic's latest Mythos class model, with cheaper prompt cache reads. Fable 5 remains available.
Read More《Cursor Docs》-Claude 4 Sonnet 1M
We recommend using Claude Sonnet 5, which also supports up to 1M tokens of context.
Read More《Cursor Docs》-Claude 4 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 6 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 5 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 5 Haiku
For stronger results, consider Claude Sonnet 5 or Gemini 3 Flash for a fast, affordable alternative.
Read More《Cursor Docs》-Kimi K3
Kimi K3 is Moonshot AI's latest open weight model. It sits above Kimi K2.7 Code for long running agent work: thorough upfront reasoning, strong one shot persistence, and the highest CursorBench score we've measured from an open model.
Read More《Cursor Docs》-Kimi K2 7 Code
We recommend using Kimi K3 for new work. K2.7 Code remains available as a lower cost Moonshot option.
Read More《Cursor Docs》-Grok 4 6
Grok 4.6 is a frontier model from Cursor and SpaceXAI for complex coding and knowledge work. It builds on Grok 4.5 with improved instruction following and long horizon agentic work.
Read More《Cursor Docs》-Grok 4 5
We recommend using Grok 4.6 for improved instruction following and long horizon agentic work. Grok 4.5 remains available.
Read More《Cursor Docs》-Gpt 5 Mini
We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.
Read More《Cursor Docs》-Gpt 5 Fast
We recommend using GPT 5.3 Codex. It's faster than previous generations and more cost effective.
Read More《Cursor Docs》-Gpt 5 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 6 Terra
GPT 5.6 Terra is the mid tier model in OpenAI's GPT 5.6 family. It sits between Sol and Luna on intelligence and price, making it a strong pick for everyday agentic coding when you want more capability than Luna without Sol's cost.
Read More《Cursor Docs》-Gpt 5 6 Sol
GPT 5.6 Sol is OpenAI's flagship GPT 5.6 model in Cursor. It is the strongest of the Sol, Terra, and Luna family: persistent on long running agent work, fast enough for interactive sessions, and notably concise in how it communicates.
Read More《Cursor Docs》-Gpt 5 6 Luna
GPT 5.6 Luna is the smallest and lowest cost model in OpenAI's GPT 5.6 family. Use it for high volume, latency sensitive, or cost sensitive agent work where Sol or Terra would be more than you need.
Read More《Cursor Docs》-Gpt 5 5
GPT 5.5 is OpenAI's most intelligent model in Cursor. It keeps momentum on long running work and stays on task for significantly longer before stopping early, which matters most in complex, multi step coding sessions.
Read More《Cursor Docs》-Gpt 5 4 Nano
GPT 5.4 Nano is the smallest and fastest model in the GPT 5.4 family. At $0.20 per million input tokens, it's built for high volume workloads where speed and cost matter more than peak reasoning. Reach for it when you need quick classification, extraction, ranking, or lightweight coding support.
Read More《Cursor Docs》-Gpt 5 4 Mini
GPT 5.4 Mini brings good performance to cost sensitive workflows.
Read More《Cursor Docs》-Gpt 5 4
GPT 5.4 is OpenAI's most capable model to date. It outperforms all other models on our internal benchmarks. For cost sensitive workflows where raw intelligence matters less, GPT 5.3 Codex remains a strong option at a lower price point.
Read More《Cursor Docs》-Gpt 5 3 Codex
GPT 5.3 Codex is OpenAI's flagship coding model. It leads Terminal Bench by a wide margin and performs on par with Opus 4.6 on our internal benchmarks, at roughly one third the price. Much faster than previous GPT generations. A strong default for most coding tasks.
Read More《Cursor Docs》-Gpt 5 2 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 2
GPT 5.2 has access to all agent tools when used with Cursor including:
Read More《Cursor Docs》-Gpt 5 1 Codex Mini
We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.
Read More《Cursor Docs》-Gpt 5 1 Codex Max
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 1 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5
We recommend using GPT 5.3 Codex. It scores higher on benchmarks, is faster, and more cost effective.
Read More《Cursor Docs》-Glm 5 2
GLM 5.2 has access to all agent tools when used with Cursor including:
Read More《Cursor Docs》-Gemini 3 Pro Image Preview
This model is used exclusively for the image generation tool inside Cursor. It is not selectable as a chat model.
Read More《Cursor Docs》-Gemini 3 Pro
We recommend using Gemini 3.1 Pro. It's the latest version with stronger multimodal capabilities and the same pricing.
Read More《Cursor Docs》-Gemini 3 Flash
Gemini 3 Flash is Google's speed optimized model. At $0.50 per million input tokens, it's one of the cheapest options available. Use it for simple coding tasks, quick edits, and executing plans written by a more capable model.
Read More《Cursor Docs》-Gemini 3 7 Flash
Gemini 3.7 Flash is Google's latest speed tier model. It pairs strong agentic coding performance with low per token costs. Use it for high throughput coding tasks that benefit from reasoning and a large context window.
Read More《Cursor Docs》-Gemini 3 6 Flash
We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model with lower input and output prices.
Read More《Cursor Docs》-Gemini 3 5 Flash
We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model with lower input and output prices.
Read More《Cursor Docs》-Gemini 3 1 Pro
Gemini 3.1 Pro is Google's latest model. It processes images alongside code, making it strong for UI/UX work from design mockups. It supports context windows up to 1M tokens.
Read More《Cursor Docs》-Gemini 2 5 Flash
We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model.
Read More《Cursor Docs》-Cursor Composer 2 5
Composer 2.5 is Cursor's own agentic model. It builds on Composer 2 with stronger intelligence on long agentic tasks, better effort calibration, tool selection, intent understanding, and reliability.
Read More《Cursor Docs》-Cursor Composer 1
We strongly recommend using Composer 2.5. It's smarter and includes more usage on individual plans.
Read More《Cursor Docs》-Claude Sonnet 5
Claude Sonnet 5 is Anthropic's latest medium tier model and replaces Sonnet 4.6. It pushes quality close to Opus while keeping Sonnet's lower per token price. It supports thinking mode and context windows up to 1M tokens, making it a strong default for everyday coding when you want frontier reasoning without Opus pricing.
Read More《Cursor Docs》-Claude Opus 5
Claude Opus 5 is Anthropic's latest Opus model and replaces Opus 4.8. It is a step change over Opus 4.8 on agentic coding, professional knowledge work, and long horizon reasoning, and it lands on par with Fable 5 on CursorBench at Opus pricing. We recommend the high thinking variant for the best results.
Read More《Cursor Docs》-Claude Opus 4 8
We recommend using Claude Opus 5. It replaces Opus 4.8 with stronger agentic coding and long horizon reasoning at the same price.
Read More《Cursor Docs》-Claude Opus 4 7 Fast
Fast mode for Claude Opus 4.7 bills at a much higher per token rate than standard Opus 4.7. Use it selectively for time sensitive or critical work where cost is secondary.
Read More《Cursor Docs》-Claude Opus 4 7
We recommend using Claude Opus 5. It is Anthropic's latest Opus release with the same pricing and stronger agentic capabilities.
Read More《Cursor Docs》-Claude Opus 4 6
We recommend using Claude Opus 5. It scores higher on CursorBench, offers stronger autonomous capabilities, and is priced the same.
Read More《Cursor Docs》-Claude Opus 4 5
We recommend using Claude Opus 5. It's the latest Opus with stronger reasoning and code quality.
Read More《Cursor Docs》-Claude Fable 5
Claude Fable 5 is Anthropic's most capable generally available model for autonomous knowledge work and coding. It is a Mythos class model with strong safeguards, built to handle long running, complex, and asynchronous tasks where earlier models needed more frequent check ins.
Read More《Cursor Docs》-Claude 4 Sonnet 1M
We recommend using Claude Sonnet 5, which also supports up to 1M tokens of context.
Read More《Cursor Docs》-Claude 4 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 6 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 5 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 5 Haiku
For stronger results, consider Claude Sonnet 5 or Gemini 3 Flash for a fast, affordable alternative.
Read More