Mistral Medium is a text-based AI model by Mistral. It features 73 tok/s output speed, $2.75/1M input tokens pricing. It scores 9.0 on the intelligence index.
Output Speed
73 tok/s
Latency (TTFT)
0.40s
Blended Price
$4.09/M
| Input (Prompt) | $2.75 |
| Output (Completion) | $8.10 |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Mistral Medium costs $2.75/1M input tokens and $8.10/1M output tokens.
Mistral Medium generates output at 73 tok/s. Time to first token is 0.40s.
No, Mistral Medium is a paid model. Check the free models page for zero-cost alternatives.
See the alternatives section above for models with similar capabilities. You can also compare Mistral Medium head-to-head with any model on our comparison page.
Last updated: