Ministral 3 (14B Reasoning 2512): API Pricing, Context Window & Benchmarks
Ministral 3 (14B 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 14B 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 (14B Reasoning 2512) benchmarks
Rankings
Quality Tracker
Ministral 3 (14B Reasoning 2512) Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sun Jul 26 2026Ministral 3 (14B Reasoning 2512) pricing
Providers
Ministral 3 (14B Reasoning 2512) starts at $0.200 per million input tokens and $0.200 per million output tokens via Mistral AI.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Mistral AI | $0.200 | $0.200 | 262.1K/262.1K | —/0.23 | 129/— | — | / |
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. Success is calculated from completed versus failed requests over the trailing seven days.
Ministral 3 (14B Reasoning 2512) model size
Ministral 3 (14B Reasoning 2512) has 14 billion parameters. See how it compares to other models in the same parameter range.
Ministral 3 (14B Reasoning 2512) context window
Input and output token limits for Ministral 3 (14B Reasoning 2512), plus how it ranks on long-context understanding.
Ministral 3 (14B Reasoning 2512) API
Available from the model provider
Ministral 3 (14B Reasoning 2512) has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationMinistral 3 (14B Reasoning 2512) latency
Ministral 3 (14B Reasoning 2512) time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Ministral 3 (14B Reasoning 2512) examples
Recent arena outputs from Ministral 3 (14B Reasoning 2512), picked from the highest-ranked matchups.
Ministral 3 (14B Reasoning 2512) license
Ministral 3 (14B Reasoning 2512) is released under the Apache 2.0 license, which permits commercial use, has 14.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 14.0B
Apache License 2.0 - allows commercial use
Ministral 3 (14B Reasoning 2512) resources
Official sources for Ministral 3 (14B Reasoning 2512): api documentation, official playground, official launch post, model weights.
Ministral 3 (14B Reasoning 2512) vs other models
The most-compared alternatives to Ministral 3 (14B Reasoning 2512) are QwQ-32B, Qwen3 VL 32B Thinking, Qwen3 VL 30B A3B Instruct. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Ministral 3 (14B Reasoning 2512)
Models ranked just above and below Ministral 3 (14B Reasoning 2512) by LLM Stats score.
FAQ
Common questions about Ministral 3 (14B Reasoning 2512).