Mistral: Mistral Medium 3.5 (batch)

Mistral Medium 3.5 (batch) is a Mistral AI model that accepts text, image, and file inputs. It offers a 262,144-token context window and allows up to 209,715 completion tokens, so long documents and lengthy outputs fit in a single request. It supports tool calling and reasoning. Structured output support is not listed, so verify it before relying on schema-constrained responses. Pricing is $0.75 per million input tokens and $3.75 per million output tokens. Because output costs five times as much as input, it suits workloads that read a lot and write relatively little, such as analyzing long files or mixed image-and-text material. Its benchmark record is thin. The blended score of 16.4 rests on a single independent benchmark, where it scored 23.4 on the AI index. Treat its quality as largely unproven and run your own evaluations before committing. Shortlist this model if you need a large context window, multimodal input, and tool use at a mid-range price.