AI model · Mistral
Ministral 3 8B 2512
Model ID: mistralai/ministral-8b-2512
- Input
- $0.15 per 1M tokens
- Output
- $0.15 per 1M tokens
- Context
- 262K tokens at once
- Max output
- 210K tokens per reply
- Released
- 2 Dec 2025 Mistral
What it can do
- NoReasoning
- YesTool calling
- YesImage input
- YesOpen weights
- NoFree to use
Takes text, image; gives text.
How its listing describes it
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Sources
- Mistral: Ministral 3 8B 2512 on OpenRouter — read 2 Oct 2026