Compare models
Up to 4 models side by side.
Provider | Mistral AI |
|---|---|
Listed Date added to OpenRouter | Dec 9, 2025 |
Input price USD per 1M tokens | $0.40 |
Output price USD per 1M tokens | $2 |
Workload cost Chat reply (2K in, 500 out) | $0.0018 |
Context window | 262K |
Max output | 210K |
Output speed tokens per second | n/a |
Time to first token seconds | n/a |
Intelligence Index Artificial Analysis Intelligence Index: a composite of reasoning, knowledge, math and coding evaluations. | n/a |
Engineering Index Artificial Analysis Engineering Index: engineering and technical problem solving. | n/a |
Inputs | text, pdf |
Open weights | Yes |
Good at | open-weights |
Notes | Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring... |
Best value in each row is highlighted. Share this page's URL to share the comparison.