Mistral Small 3.2 is a text-based AI model by Mistral. It features 184 tok/s output speed, $0.10/1M input tokens pricing. It scores 15.1 on the intelligence index.
Output Speed
184 tok/s
Latency (TTFT)
0.30s
Blended Price
$0.15/M
| Input (Prompt) | $0.10 |
| Output (Completion) | $0.30 |
| 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 Small 3.2 costs $0.10/1M input tokens and $0.30/1M output tokens.
Mistral Small 3.2 has a lower coding score of 13.3. For demanding coding tasks, consider a model with a higher coding benchmark.
Mistral Small 3.2 generates output at 184 tok/s. Time to first token is 0.30s.
No, Mistral Small 3.2 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 Mistral Small 3.2 head-to-head with any model on our comparison page.