Mistral: Magistral Medium 2506

Text input Text output
Author's Description

Magistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.

Key Specifications
Cost
$$$$$
Context
40K
Released
Jun 07, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tool Choice Reasoning Include Reasoning Response Format Seed Top P Temperature Tools Structured Outputs Stop Max Tokens Frequency Penalty Presence Penalty
Features

This model supports the following features:

Tools Reasoning Response Format Structured Outputs
Performance Summary

Mistral: Magistral Medium 2506, Mistral's first reasoning model, demonstrates a strong overall performance profile, particularly excelling in reliability with a perfect 100% success rate across all benchmarks, indicating consistent and usable responses. In terms of speed, it performs among the fastest models, ranking in the 71st percentile. Its pricing is moderate, placing it in the 24th percentile, suggesting a balanced cost-effectiveness. The model exhibits notable strengths in several key areas. It shows exceptional accuracy in Hallucinations (98.0%) and Ethics (99.0%), indicating a strong ability to acknowledge uncertainty and adhere to ethical principles. Its General Knowledge (98.5%) and Email Classification (99.0%) also stand out with high accuracy. While its accuracy in Instruction Following (58.0%) and Reasoning (76.0%) is respectable, these areas present opportunities for further enhancement, especially given its description as a reasoning model. The model's duration for tasks like Hallucinations and Reasoning is on the higher side, suggesting that while it processes complex tasks, it may take longer to do so. Its cost for Email Classification is remarkably low, placing it in the 5th percentile, making it highly competitive for this specific task.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $2
Completion $5

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Mistral
Mistral | mistralai/magistral-medium-2506 40K $2 / 1M tokens $5 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by mistralai