Devstral Medium is a text-based AI model by Mistral. It features 131 tok/s output speed, $0.40/1M input tokens pricing. It scores 18.7 on the intelligence index.
Output Speed
131 tok/s
Latency (TTFT)
0.40s
Blended Price
$0.80/M
| Input (Prompt) | $0.40 |
| Output (Completion) | $2.00 |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Devstral Medium costs $0.40/1M input tokens and $2.00/1M output tokens.
Devstral Medium has a lower coding score of 15.9. For demanding coding tasks, consider a model with a higher coding benchmark.
Devstral Medium generates output at 131 tok/s. Time to first token is 0.40s.
No, Devstral Medium is a paid model. Check the free models page for zero-cost alternatives.
Last updated:
See the alternatives section above for models with similar capabilities. You can also compare Devstral Medium head-to-head with any model on our comparison page.