Mistral: Ministral 3 3B 2512
Ministral 3 3B 2512 is a text-and-image input model from Mistral AI with a 131,072-token context window. It supports tool use, which makes it usable in agentic workflows, but it does not support reasoning modes and structured output support is unconfirmed. The maximum completion token count is not specified, so developers should verify output limits before committing to production use cases. At $0.10 per million tokens for both input and output, the pricing is low and consistent, making it a candidate for high-volume or cost-sensitive applications. However, there is currently no independent benchmark coverage to substantiate performance claims, so buyers cannot compare it against peers on standardized tasks. Teams comfortable running their own evaluations may find the price worth testing, but anyone relying on third-party benchmarks to make a decision should treat this model as unproven for now.
- Model ID
- mistralai/ministral-3b-2512
- Vendor
- mistralai
- Tokenizer
- Mistral
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- default
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no