Mistral: Ministral 3 3B 2512
Analysis Summary
Mistral Ministral 3 3B 2512 is a compact 3B-parameter model from Mistral with vision, tool use, and function calling support at $0.10 per million tokens for both input and output. For its size, it offers a broad capability surface, but reasoning, coding, and math scores are low, and agentic performance is limited despite a moderate agentic index.
For businesses, this model is best suited to simple automation tasks, lightweight content classification, or low-stakes tool-use pipelines where cost is the primary constraint. It is not appropriate for complex reasoning, coding workflows, or client-facing content where quality matters. The 131K context window is a positive for document-length inputs.
At this price point, Ministral 3 3B 2512 is one of the cheapest multimodal options available. Teams needing a fast, cheap model for simple structured tasks with occasional image inputs will find it useful, but most business workflows will require a larger model.
Assessed June 6, 2026
Editorial notes
Mistral Ministral 3 3B 2512 is a very small, cheap multimodal model with tool use and vision support, suited to lightweight automation tasks, but reasoning and coding capability are limited.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Mistral: Ministral 3 3B 2512 compares
Mistral: Ministral 3 3B 2512 ranks #296 of 378 AI models we track for overall intelligence, #278 of 315 for coding, #158 of 289 for agentic tasks. Its 131K-token context window is larger than 60% of the models we list. At $0.10 per million input tokens it is cheaper than 66% of comparable models.
About Mistral: Ministral 3 3B 2512
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Mistral: Ministral 3 3B 2512 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
mistralai/ministral-3b-2512
|
| Provider | mistralai |
| Release Date | December 2, 2025 |
| Context Length | 131,072 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.10 | $0.000100 |
| Output | $0.10 | $0.000100 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Mistral: Ministral 3 3B 2512
How much does Mistral: Ministral 3 3B 2512 cost?
Mistral: Ministral 3 3B 2512 costs $0.10 per million input tokens and $0.10 per million output tokens.
What is the context window of Mistral: Ministral 3 3B 2512?
Mistral: Ministral 3 3B 2512 has a context window of 131,072 tokens (131K).
Is Mistral: Ministral 3 3B 2512 good for coding?
On our coding benchmark index, Mistral: Ministral 3 3B 2512 ranks #278 of 315 models, placing it in the broader range of the field for code generation and debugging.
What can Mistral: Ministral 3 3B 2512 do?
Mistral: Ministral 3 3B 2512 supports image/vision input, tool use, and function calling.
Who created Mistral: Ministral 3 3B 2512?
Mistral: Ministral 3 3B 2512 is developed by Mistral and was released on December 2, 2025.
