Skip to main content

Pricing and rate limits

Pay-as-you-go

The prices listed below are exclusive of VAT.

Chat Completions API

ModelEndpointInput (USD)Output (USD)Input (EUR)Output (EUR)
Mistral 7Bopen-mistral-7b0.25$ / 1M tokens0.25$ / 1M tokens0.2€ / 1M tokens0.2€ / 1M tokens
Mixtral 8x7Bopen-mixtral-8x7b0.7$ / 1M tokens0.7$ / 1M tokens0.65€ / 1M tokens0.65€ / 1M tokens
Mistral Smallmistral-small-latest2$ / 1M tokens6$ / 1M tokens1.85€ / 1M tokens5.55€ / 1M tokens
Mistral Mediummistral-medium-latest2.7$ / 1M tokens8.1$ / 1M tokens2.5€ / 1M tokens7.5€ / 1M tokens
Mistral Largemistral-large-latest8$ / 1M tokens24$ / 1M tokens7.3€ / 1M tokens22€ / 1M tokens

Embeddings API

ModelEndpointInput (USD)Input (EUR)
Mistral Embedmistral-embed0.1$ / 1M tokens0.1€ / 1M tokens

Rate limits

All endpoints have a rate limit of 5 requests per second, 2 million tokens per minute, and 10,000 million tokens per month. You can check your current rate limits on the platform. If you need to increase them, please contact support with your estimated consumption and use case.

We will raise the limits for embedding models in the future.