Magistral Small 1.2 is a text-based AI model by Mistral. It features 102 tok/s output speed, $0.50/1M input tokens pricing. It scores 18.2 on the intelligence index.
Output Speed
102 tok/s
Latency (TTFT)
0.33s
Blended Price
$0.75/M
| Input (Prompt) | $0.50 |
| Output (Completion) | $1.50 |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Magistral Small 1.2 costs $0.50/1M input tokens and $1.50/1M output tokens.
Magistral Small 1.2 has a lower coding score of 14.8. For demanding coding tasks, consider a model with a higher coding benchmark.
Magistral Small 1.2 generates output at 102 tok/s. Time to first token is 0.33s.
No, Magistral Small 1.2 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 Magistral Small 1.2 head-to-head with any model on our comparison page.