Compare models
Up to 4 models side by side.
Provider | Mistral AI |
|---|---|
Listed Date added to OpenRouter | Mar 16, 2026 |
Input price USD per 1M tokens | $0.15 |
Output price USD per 1M tokens | $0.60 |
Workload cost Chat reply (2K in, 500 out) | $0.0006 |
Context window | 262K |
Max output | 210K |
Output speed tokens per second | 141 |
Time to first token seconds | 1.61s |
Intelligence Index Artificial Analysis Intelligence Index: a composite of reasoning, knowledge, math and coding evaluations. | 4.3 |
Engineering Index Artificial Analysis Engineering Index: engineering and technical problem solving. | 13.3 |
Inputs | text, image |
Open weights | Yes |
Good at | visionopen-weightslow-cost |
Notes | Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from... |
Best value in each row is highlighted. Share this page's URL to share the comparison.