Min istral 3 (3B Reasoning 2512): API Pricing, Context Window & Benchmarks
Min istral 3 (3B Reasoning 2512) is a language model from Mistral, released in December 2025, with multimodal input.
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. This model is the reasoning post-trained version, trained for reasoning tasks, making it ideal for math,
Min istral 3 (3B Reasoning 2512) benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
How Min istral 3 (3B Reasoning 2512) performs across real-world prompt categories.
Performance by conversation depth
How Min istral 3 (3B Reasoning 2512) holds up as conversations get longer.
Quality Tracker
Min istral 3 (3B Reasoning 2512) Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Aug 25 2026Min istral 3 (3B Reasoning 2512) pricing
Providers
Min istral 3 (3B Reasoning 2512) starts at $0.100 per million input tokens and $0.100 per million output tokens via Mistral AI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Mistral AI | $0.100 | — | $0.100 | 131.1K/131.1K | 0.16 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Min istral 3 (3B Reasoning 2512) model size
Min istral 3 (3B Reasoning 2512) has 3 billion parameters. See how it compares to other models in the same parameter range.
Min istral 3 (3B Reasoning 2512) context window
Input and output token limits for Min istral 3 (3B Reasoning 2512), plus how it ranks on long-context understanding.
Min istral 3 (3B Reasoning 2512) API
Available from the model provider
Min istral 3 (3B Reasoning 2512) has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationMin istral 3 (3B Reasoning 2512) latency
Min istral 3 (3B Reasoning 2512) time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Min istral 3 (3B Reasoning 2512) examples
Recent arena outputs from Min istral 3 (3B Reasoning 2512), picked from the highest-ranked matchups.
Min istral 3 (3B Reasoning 2512) license
Min istral 3 (3B Reasoning 2512) is released under the Apache 2.0 license, which permits commercial use, has 3.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 3.0B
Apache License 2.0 - allows commercial use
Min istral 3 (3B Reasoning 2512) resources
Official sources for Min istral 3 (3B Reasoning 2512): api documentation, official playground, official launch post, model weights.
Min istral 3 (3B Reasoning 2512) vs other models
The most-compared alternatives to Min istral 3 (3B Reasoning 2512) are Kimi-k1.5, Llama 3.1 Nemotron Ultra 253B v1, GPT-4o. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Min istral 3 (3B Reasoning 2512)
Models ranked just above and below Min istral 3 (3B Reasoning 2512) by LLM Stats score.
FAQ
Common questions about Min istral 3 (3B Reasoning 2512).