Medium 3.1
MistralBalanced
Tool UseVisionStructured Output
About this model
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...
Performance Tier
Balanced
Medium 3.1 is a balanced model from Mistral : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.400 |
| Output (completion) | $2.00 |
| Cache read | $0.040 |
Capabilities
Context Length131K
Max Output Tokens—
TokenizerMistral
Inputtext, image
Outputtext
Release DateAugust 13, 2025
Benchmarks
General Intelligence
MMLU
82%
Mathematics
MATH-500
85%
Programming
HumanEval
88%
Recommended Use Cases
General ChatCodingTranslationSummarization
Strengths
- Good balance of performance and cost in the Mistral lineup
- Strong multilingual support including French
- Reliable for everyday coding and analysis tasks
Limitations
- Outperformed by Mistral Large on complex tasks
- Smaller model with more limited reasoning depth
Resources
This model may use your data for training
