Benchable
Text input
Text output
Description
Magistral Small is a 24B parameter instruction-tuned model based on Mistral-Small-3.1 (2503), enhanced through supervised fine-tuning on traces from Magistral Medium and further refined via reinforcement learning. It is optimized for reasoning and supports a wide multilingual range, including over 20 languages.
Key Specifications
Context Length
40K
Parameters
24B (Rumoured)
Created
Jun 10, 2025
Hugging Face
mistralai/Magistral-Small-2506Supported Parameters
This model supports the following parameters:
Reasoning
Structured Outputs
Temperature
Tools
Tool Choice
Include Reasoning
Response Format
Presence Penalty
Max Tokens
Top P
Seed
Stop
Frequency Penalty
Features
This model supports the following features:
Structured Outputs
Response Format
Reasoning
Tools
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.5 |
| Completion | $1.5 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Mistral
|
Mistral | mistralai/magistral-small-2506 | 40K | $0.5 / 1M tokens | $1.5 / 1M tokens |
Benchmark Performance Summary
| Benchmark | Category | Reasoning | Free | Executions | Accuracy | Cost | Duration |
|---|