Start typing to search.
Average response time
22.73 s
Estimated 500-token answer. Across 17 models with recent complete speed data.
Average response start
0.73 s
Wait until the first token. Across 17 models with recent response start data.
Average output speed
44.3 tok/s
Generated tokens per second. Across 17 models with recent output speed data.
Prices and recent speed measurements below are for Mistral endpoints. A 500-token response combines the wait for the first token with the time to generate 500 output tokens.
Model data fetched .
Practical comparison guide
Mistral currently has 21 indexed models on this site, including 17 text, 2 embeddings, 1 transcription, 1 speech. This page combines the provider-specific catalog with published pricing and recent performance data so you can identify suitable models and then compare Mistral with alternative hosts on each model page.
Mistral offers model-specific routes rather than one interchangeable service. Check modality, context window, supported inputs, and parameter support before comparing price. The largest published context window in this catalog is 262.1K tokens.
The lowest published input price shown here is $0.1 / 1M tokens. Recent 500-token response measurements are available for 17 models; missing measurements remain visible and are never estimated.
Mistral lists its headquarters as FR. Published datacenter coverage: no datacenter regions are currently published. Headquarters and hosting regions describe different things, so verify data residency, service terms, and current availability directly with the provider.
