Mistral
Magistral Small 1.2
Mistral reasoning model for transparent analysis, math, and complex decisions
Model facts
- Context window
- 128K tokens
- Maximum output
- 4K tokens
- Cheapest paid input
- $0.5 per 1M tokens
- Cheapest paid output
- $1.5 per 1M tokens
- Open weights
- yes
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text, image.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 11.5 | 14.7 | 80.3 | not measured |
Observed price history
- 2026-08-24: $0.5 input / $1.5 output per 1M tokens
API providers
- Amazon Bedrock — model id mistral.magistral-small-2509; $0.5 input / $1.5 output per 1M tokens; provider documentation