Models

Available models in Cursor

Cursor supports all frontier coding models from all major model providers.

Model List

Claude 4 Sonnet

Normal Mode

• Provider: Anthropic
• Link: Claude 4 Sonnet
• Context Window: 120k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Cost: 1 requests/message
• Notes: Currently not available in slow pool

Variants

• Thinking:
  • Cost: 2 requests/message

Max Mode

• Provider: Anthropic
• Link: Claude 4 Sonnet
• Context Window: 200k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Input Cost: 90 requests/MTok
• Cached Input Cost: 9 requests/MTok
• Output Cost: 450 requests/MTok

Claude 4 Opus

Max Mode

• Provider: Anthropic
• Link: Claude 4 Opus
• Context Window: 200k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Input Cost: 450 requests/MTok
• Cached Input Cost: 45 requests/MTok
• Output Cost: 2250 requests/MTok

Claude 3.7 Sonnet

Normal Mode

• Provider: Anthropic
• Link: Claude 3.7 Sonnet
• Context Window: 120k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Trait: Powerful but eager to make changes
• Cost: 1 requests/message

Variants

• Thinking:
  • Cost: 2 requests/message
  • Notes: More requests due to token intensive

Max Mode

• Provider: Anthropic
• Link: Claude 3.7 Sonnet
• Context Window: 200k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Trait: Powerful but eager to make changes
• Input Cost: 90 requests/MTok
• Cached Input Cost: 9 requests/MTok
• Output Cost: 450 requests/MTok

Claude 3.5 Sonnet

Normal Mode

• Provider: Anthropic
• Link: Claude 3.5 Sonnet
• Context Window: 75k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Trait: Great all rounder for most tasks
• Cost: 1 requests/message

Max Mode

• Provider: Anthropic
• Link: Claude 3.5 Sonnet
• Context Window: 200k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Trait: Great all rounder for most tasks
• Input Cost: 90 requests/MTok
• Cached Input Cost: 9 requests/MTok
• Output Cost: 450 requests/MTok

Claude 3.5 Haiku

Normal Mode

• Provider: Anthropic
• Link: Claude 3.5 Haiku
• Context Window: 60k
• Cost: 0.3333333333333333 requests/message

Claude 3 Opus

Normal Mode

• Provider: Anthropic
• Link: Claude 3 Opus
• Context Window: 60k
• Capabilities: Thinking (uses reasoning tokens)
• Cost: 2.5 requests/message

Cursor Small

Normal Mode

• Provider: Cursor
• Link: Cursor Small
• Context Window: 60k
• Cost: 0 requests/message

Deepseek V3

Normal Mode

• Provider: DeepSeek
• Link: Deepseek V3
• Context Window: 60k
• Capabilities: Agent (can use tools)
• Cost: 0 requests/message

Deepseek V3.1

Normal Mode

• Provider: DeepSeek
• Link: Deepseek V3.1
• Context Window: 60k
• Capabilities: Agent (can use tools)
• Cost: 0 requests/message

Deepseek R1

Normal Mode

• Provider: DeepSeek
• Link: Deepseek R1
• Context Window: 60k
• Capabilities: Thinking (uses reasoning tokens)
• Cost: 1 requests/message

Deepseek R1 (05/28)

Normal Mode

• Provider: DeepSeek
• Link: Deepseek R1 (05/28)
• Context Window: 60k
• Capabilities: Thinking (uses reasoning tokens)
• Cost: 1 requests/message

Gemini 2.5 Pro

Normal Mode

• Provider: Google
• Link: Gemini 2.5 Pro
• Context Window: 120k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Trait: Careful and precise
• Cost: 1 requests/message
• Notes: Variable pricing depending on token count

Max Mode

• Provider: Google
• Link: Gemini 2.5 Pro
• Context Window: 1M
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Trait: Careful and precise
• Input Cost: 37.5 requests/MTok
• Cached Input Cost: 9.3 requests/MTok
• Output Cost: 300 requests/MTok

Variants

• Long Context (>200k):
  • Input Cost: 75 requests/MTok
  • Cached Input Cost: 18.75 requests/MTok
  • Output Cost: 450 requests/MTok

Gemini 2.5 Flash

Normal Mode

• Provider: Google
• Link: Gemini 2.5 Flash
• Context Window: 1M
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Cost: 0 requests/message

Max Mode

• Provider: Google
• Link: Gemini 2.5 Flash
• Context Window: 1M
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Input Cost: 4.5 requests/MTok
• Cached Input Cost: 1.13 requests/MTok
• Output Cost: 105 requests/MTok

Gemini 2.0 Pro (exp)

Normal Mode

• Provider: Google
• Link: Gemini 2.0 Pro (exp)
• Context Window: 60k
• Capabilities: Thinking (uses reasoning tokens)
• Cost: 1 requests/message

GPT-4o

Normal Mode

• Provider: OpenAI
• Link: GPT-4o
• Context Window: 60k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Cost: 1 requests/message

Max Mode

• Provider: OpenAI
• Link: GPT-4o
• Context Window: 128k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Input Cost: 75 requests/MTok
• Cached Input Cost: 37.5 requests/MTok
• Output Cost: 300 requests/MTok

GPT-4o mini

Normal Mode

• Provider: OpenAI
• Link: GPT-4o mini
• Context Window: 60k
• Cost: 0 requests/message
• Notes: 500 requests/day with free plan

GPT 4.5 Preview

Normal Mode

• Provider: OpenAI
• Link: GPT 4.5 Preview
• Context Window: 60k
• Capabilities: Thinking (uses reasoning tokens)
• Cost: 50 requests/message

GPT 4.1

Normal Mode

• Provider: OpenAI
• Link: GPT 4.1
• Context Window: 128k
• Capabilities: Agent (can use tools)
• Cost: 1 requests/message

Max Mode

• Provider: OpenAI
• Link: GPT 4.1
• Context Window: 1M
• Capabilities: Agent (can use tools)
• Input Cost: 60 requests/MTok
• Cached Input Cost: 15 requests/MTok
• Output Cost: 240 requests/MTok

o1

Normal Mode

• Provider: OpenAI
• Link: o1
• Context Window: 60k
• Capabilities: Thinking (uses reasoning tokens)
• Cost: 10 requests/message

o1 Mini

Normal Mode

• Provider: OpenAI
• Link: o1 Mini
• Context Window: 60k
• Capabilities: Thinking (uses reasoning tokens)
• Cost: 2.5 requests/message

o3

Normal Mode

• Provider: OpenAI
• Link: o3
• Context Window: 128k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Cost: 1 requests/message
• Notes: High reasoning effort

Max Mode

• Provider: OpenAI
• Link: o3
• Context Window: 200k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Input Cost: 60 requests/MTok
• Cached Input Cost: 15 requests/MTok
• Output Cost: 240 requests/MTok

o3-mini

Normal Mode

• Provider: OpenAI
• Link: o3-mini
• Context Window: 60k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Cost: 0.25 requests/message
• Notes: High reasoning effort

o4-mini

Normal Mode

• Provider: OpenAI
• Link: o4-mini
• Context Window: 128k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Cost: 1 requests/message
• Notes: High reasoning effort

Max Mode

• Provider: OpenAI
• Link: o4-mini
• Context Window: 200k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Input Cost: 33 requests/MTok
• Cached Input Cost: 8.25 requests/MTok
• Output Cost: 132 requests/MTok

Grok 2

Normal Mode

• Provider: xAI
• Link: Grok 2
• Context Window: 60k
• Cost: 1 requests/message

Grok 3 Beta

Normal Mode

• Provider: xAI
• Link: Grok 3 Beta
• Context Window: 60k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Cost: 1 requests/message

Max Mode

• Provider: xAI
• Link: Grok 3 Beta
• Context Window: 132k
• Capabilities: Agent (can use tools), Thinking (uses reasoning tokens)
• Input Cost: 90 requests/MTok
• Output Cost: 450 requests/MTok

Grok 3 Mini

Normal Mode

• Provider: xAI
• Link: Grok 3 Mini
• Context Window: 60k
• Capabilities: Agent (can use tools)
• Cost: 0 requests/message

Max Mode

• Provider: xAI
• Link: Grok 3 Mini
• Context Window: 132k
• Capabilities: Agent (can use tools)
• Input Cost: 9 requests/MTok
• Cached Input Cost: 9 requests/MTok
• Output Cost: 30 requests/MTok

Auto

Enabling Auto configures Cursor to select the premium model best fit for the immediate task and with the highest reliability based on current demand. This feature can detect degraded output performance and automatically switch models to resolve it.

Context windows

A context window is the maximum span of tokens (text and code) an LLM can consider at once, including both the input prompt and output generated by the model.

Each chat in Cursor maintains its own context window. The more prompts, attached files, and responses included in a session, the larger the context window grows.

Max Mode

Normally, Cursor uses a context window of 128k tokens (~10,000 lines of code). Max Mode is our option to turn on the maximum context windows for all models. This will be a bit slower and more expensive. It is most relevant for Gemini 2.5 Pro and GPT 4.1, which have 1M token context windows.

FAQ

Where are models hosted?

Models are hosted on US-based infrastructure by the model’s provider, a trusted partner or Cursor.

When Privacy Mode is enabled, neither Cursor nor model providers store your data. All data is deleted after each request. For details see our Privacy, Privacy Policy, and Security pages.

Assistant

Responses are generated using AI and may contain mistakes.