Skip to content
Mistral

Magistral Small / Medium

flagship
Mistral · released 2025-06-01 · text
currently routing · 4.2k rpm
128M tokens
Context
— / 1M
Input
— / 1M
Output
— t/s
Speed
open
License
/ ABOUT

Mistral Magistral Small is a compact reasoning model from Mistral AI that uses chain-of-thought processing to deliver improved accuracy on complex analytical tasks. The Small variant provides efficient inference while maintaining strong reasoning capabilities for its size class.

The model excels at multi-step reasoning, mathematical problem solving, logical deduction, and structured analysis. It produces detailed reasoning traces that help users understand its thought process, making it suitable for applications where explainability matters.

Magistral Small is ideal for developers needing reasoning capabilities without the cost of larger models, offering an efficient option for everyday analytical tasks.

BENCHMARKS Artificial Analysis Index
Intelligence 18

Providers for Magistral Small / Medium

2 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider
Context
Quant
Uptime · 30d
bf16
0.00%
bf16
0.00%