models/mistral/mistral-medium-3-1
M
Mistral·active

Mistral Medium 3.1

Mistral's mid-tier model. Context window: 131K tokens.

Overall score
4.23
/5.00 · ranked #39
Input
$0.400
per 1M tokens
Output
$2.00
per 1M tokens
Context
131K
tokens
Blended
$1.60
3:1 out:in ratio

Price drops, new benchmarks, model updates. Stay current on Mistral Medium 3.1.

One email per change. Unsubscribe anytime.

modelpicker.aipowered by live benchmark data

Scores by test

Methodology →
Structured Output
4.0
Strategic Analysis
5.0
Constrained Rewriting
5.0
Creative Problem Solving
3.0
Tool Calling
4.0
Faithfulness
4.0
Classification
4.0
Long Context
5.0
Safety Calibration
2.0
Persona Consistency
5.0
Agentic Planning
5.0
Multilingual
5.0
Tabular Data
4.0

What you need to know

Mistral Medium 3.1 is optimized for high-complexity logical tasks and long-form processing. It achieves perfect internal scores in strategic analysis, agentic planning, and constrained rewriting, making it highly effective for structured workflows and complex reasoning. Its 131K context window is backed by a 5/5 long-context score, ensuring reliability when processing large datasets or extensive documentation.

The model is priced at a blended cost of $1.60/MTok, positioning it as a mid-tier option. Given its performance in strategic and multilingual tasks, it offers a strong value proposition for developers who need reasoning capabilities close to frontier models without the associated cost of top-tier proprietary APIs.

There are notable trade-offs in safety and creativity. A 2/5 score in safety calibration suggests a higher likelihood of bypassing guardrails, which may require additional filtering layers for public-facing applications. Additionally, its 3/5 score in creative problem solving indicates it is better suited for deterministic tasks than open-ended generative work.

Use this model if your application requires rigorous agentic planning, multilingual support, or precise rewriting of large documents. Skip this model if your use case requires high safety constraints or high-variance creative output.

Strengths — Top 3

Strategic Analysis5.0/5.0
Constrained Rewriting5.0/5.0
Long Context5.0/5.0

Relative weaknesses — Bottom 3

Safety Calibration2.0/5.0
Creative Problem Solving3.0/5.0
Structured Output4.0/5.0

Similar models

OGPT-4.1 Mini$1.303.92QQwen: Qwen3.6 Plus$1.544.54OGPT-4.1$6.504.23OGPT-5.1$7.814.23