Mistral: Mistral Small 4
Mistral Small 4 is a text-and-image input model from Mistral AI with a 262,144-token context window, tool use, and reasoning support. Structured output support is unconfirmed based on available data. The large context window makes it a candidate for long-document tasks, and the multimodal input handling extends it beyond text-only workflows. At $0.15 per million input tokens and $0.60 per million output tokens, it sits at the budget end of the market. Its blended benchmark score of 6.1 is drawn from only one independent benchmark, so performance claims should be treated as provisional. Teams running high-volume pipelines on a tight budget may find the pricing attractive, but buyers who need confidence across a broad range of tasks should wait for wider benchmark coverage before committing.
- Model ID
- mistralai/mistral-small-2603
- Vendor
- mistralai
- Tokenizer
- Mistral
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- default
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
Category rankings
Where Mistral: Mistral Small 4 places across the 5 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #11 | Self-Hosted / LocalCost · of 25 ranked | 117 |
| #18 | Social Media PostsWriting · of 25 ranked | 119 |
| #18 | Voice Assistant BackendVoice · of 25 ranked | 123 |
| #18 | Cheap Bulk InferenceCost · of 25 ranked | 137 |
| #19 | Real-Time ChatLatency · of 25 ranked | 117 |