Mistral Small 4
MistralBalanced
ThinkingTool UseVisionStructured Output
About this model
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
Performance Tier
Balanced
Mistral Small 4 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 plansAffordable
Low cost. Suitable for sustained use and high-volume interactions.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.150 |
| Output (completion) | $0.600 |
| Cache read | $0.015 |
Capabilities
Context Length262K
Max Output Tokens—
TokenizerMistral
Inputtext, image
Outputtext
Release DateMarch 16, 2026
Benchmarks
General Intelligence
MMLU
Not reported
GPQA Diamond
71.2%
Mathematics
MATH-500
Not reported
Programming
HumanEval
Not reported
Where does Mistral Small 4 stand?
Compare its performance index against every other model.
Recommended Use Cases
General ChatCodingTranslationAnalysisCustomer Support
Strengths
- First Mistral model to unify reasoning (Magistral), vision (Pixtral), and coding (Devstral)
- Extremely cost-efficient — only 6B active parameters from 119B MoE (128 experts)
- 256K context window with configurable reasoning effort (none/low/medium/high)
- Open-weight Apache 2.0 license, EU-based — ideal for GDPR compliance
Limitations
- Limited published benchmark coverage — GPQA Diamond is the only score reported in Mistral's official evaluation
- Outperformed by Mistral Large on complex reasoning tasks
Frequently asked questions
Resources
This model may use your data for training
