Mistral: Mistral Small 3

Mistral Small 3 is a text-only model from Mistral AI with a 32,768-token context window and a maximum completion length of 16,384 tokens. It does not support tool use, reasoning modes, or structured output, which narrows its fit to straightforward text generation and completion tasks. If your workflow depends on function calling, JSON schema outputs, or multi-step reasoning pipelines, this model will not cover those requirements. At $0.05 per million input tokens and $0.08 per million output tokens, Mistral Small 3 sits at a very low price point, making it worth considering for high-volume, low-complexity workloads where cost control matters more than capability depth. However, its blended benchmark score of 28.8 is derived from only one benchmark, so performance comparisons should be treated with caution. Buyers who need broader validation before committing should test it directly against their own tasks rather than relying on the limited benchmark coverage available.