Models
Cursor supports all frontier coding models from all major model providers.
| Name | Default Context | Max Mode | |
|---|---|---|---|
Claude 4.6 Opus | 200k | 1M | |
Claude 4.6 Sonnet | 200k | 1M | |
Composer 1.5 | 200k | - | |
Gemini 3 Flash | 200k | 1M | |
Gemini 3.1 Pro | 200k | 1M | |
GPT-5.2 | 272k | - | |
GPT-5.3 Codex | 272k | - | |
Grok Code | 256k | - |
Model pricing
Cursor plans include usage at the model API rates. For example, $20 of included usage on the Pro plan will be consumed based on your model selection and its price.
Usage limits are shown in editor based on your current consumption. All prices are per million tokens.
| Name | ||||
|---|---|---|---|---|
Claude 4.6 Opus | $5 | $6.25 | $0.5 | $25 |
Claude 4.6 Sonnet | $3 | $3.75 | $0.3 | $15 |
Composer 1.5 | $3.5 | - | $0.35 | $17.5 |
Gemini 3 Flash | $0.5 | - | $0.05 | $3 |
Gemini 3.1 Pro | $2 | - | $0.2 | $12 |
GPT-5.2 | $1.75 | - | $0.175 | $14 |
GPT-5.3 Codex | $1.75 | - | $0.175 | $14 |
Grok Code | $0.2 | - | $0.02 | $1.5 |
These prices are from the model's API documentation:
Auto
Enabling Auto allows Cursor to select the 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.
Auto consumes usage at the following API rates:
- Input + Cache Write: $1.25 per 1M tokens
- Output: $6.00 per 1M tokens
- Cache Read: $0.25 per 1M tokens
Both the editor and dashboard will show your usage, which includes Auto. If you prefer to select a model directly, usage is incurred at that model's list API price.
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 more context is added, filling up the available context window.
Learn more about working with context in Cursor.
Max Mode
Max Mode extends the context window to the maximum a model supports. More context gives models deeper understanding of your codebase, leading to better results on complex tasks. The models table above shows each model's maximum context size.
Max Mode uses token-based pricing at the model's API rate plus a 20% upcharge. Learn more about Max Mode.