Mistral rate limits, context window & usage caps by plan
Rate limits, context window, message limits, file upload caps and image generation limits — all plans compared.
Compare free tiers across all AI tools →Context window explained: Mistral's context window is 32000 tokens — that's ~24K wordsof text the model can "see" at once, including your conversation history.
FreeFree
View status →| Rpm | 1 requests/min | Free API tier |
| Tpm | 500000 tokens/min | Free API tier |
| Context Window | 32000 tokens(~24K words) | Mistral 7B Instruct |
| Max Tokens Output | 8192 tokens | Per response |
| Models Available | 2 models | Mistral 7B, Mixtral 8x7B |
Pro$14.99/month
View status →| Rpm | 60 requests/min | Paid API tier |
| Tpm | 2000000 tokens/min | Paid API tier |
| Context Window | 128000 tokens(~96K words) | Mistral Large |
| Max Tokens Output | 8192 tokens | Per response |
| Models Available | 5 models | All Mistral models |
About Mistral limits
Mistral enforces usage limits to manage server load and ensure fair access across all users. Limits vary significantly by plan tier — free plans are the most restricted while paid plans offer higher caps or unlimited access. Limits shown here are updated manually when Mistral AI announces changes.
Check the Mistral live status and outage history to see if current limits are being affected by an outage.