Ministral 3 (8B Reasoning 2512): Benchmarks, Pricing & Context Window
Ministral 3 (8B Reasoning 2512) is a language model from Mistral, released in December 2025, with multimodal input.
A balanced model in the Ministral 3 family, Ministral 3 8B 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,
Ministral 3 (8B Reasoning 2512) benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Ministral 3 (8B Reasoning 2512) across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Ministral 3 (8B Reasoning 2512) holds up as conversations get longer.
Quality Tracker
Ministral 3 (8B Reasoning 2512) Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Wed Oct 14 2026Ministral 3 (8B Reasoning 2512) pricing
Providers
Ministral 3 (8B Reasoning 2512) starts at $0.150 per million input tokens and $0.150 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 | $0.150 | — | $0.150 | 262.1K/262.1K | 0.34 | — | / |
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.
Ministral 3 (8B Reasoning 2512) model size
Ministral 3 (8B Reasoning 2512) has 8 billion parameters. See how it compares to other models in the same parameter range.
Ministral 3 (8B Reasoning 2512) context window
Input and output token limits for Ministral 3 (8B Reasoning 2512), plus how it ranks on long-context understanding.
Try now
huggleMake it with
Ministral 3 (8B Reasoning 2512).
Ministral 3 (8B Reasoning 2512) latency
Ministral 3 (8B Reasoning 2512) time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Ministral 3 (8B Reasoning 2512) examples
Recent arena outputs from Ministral 3 (8B Reasoning 2512), picked from the highest-ranked matchups.
Ministral 3 (8B Reasoning 2512) license
Ministral 3 (8B Reasoning 2512) is released under the Apache 2.0 license, which permits commercial use, has 8.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 8.0B
Apache License 2.0 - allows commercial use
Ministral 3 (8B Reasoning 2512) resources
Official sources for Ministral 3 (8B Reasoning 2512): provider documentation, official playground, official launch post, model weights.
Ministral 3 (8B Reasoning 2512) vs other models
The most-compared alternatives to Ministral 3 (8B Reasoning 2512) are o1-pro, MiMo-V2.5-Pro, DeepSeek R1 Zero. Open any pair side-by-side for benchmarks, pricing, context, and latency.
- Ministral 3 (8B Reasoning 2512)vso1-pro
- Ministral 3 (8B Reasoning 2512)vsMiMo-V2.5-Pro
- Ministral 3 (8B Reasoning 2512)vsDeepSeek R1 Zero
- Ministral 3 (8B Reasoning 2512)vsDeepSeek R1 Distill Llama 70B
- Ministral 3 (8B Reasoning 2512)vsDeepSeek R1 Distill Qwen 32B
- Ministral 3 (8B Reasoning 2512)vsClaude 3.5 Sonnet
Models like Ministral 3 (8B Reasoning 2512)
Models ranked just above and below Ministral 3 (8B Reasoning 2512) by LLM Stats score.
FAQ
Common questions about Ministral 3 (8B Reasoning 2512).