All Models

mistral medium 3.5@eu

mistral-mediumReasoningTool CallingAttachmentsStructured Output

Mistral Medium 3.5 is a dense 128B instruction following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. It is particularly strong at reliable multi tool calling and long horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self hostable on as few as four GPUs and available under open weights.

Providers1
ReleasedApr 30, 2026
Input Modalitiestext, image
Output Modalitiestext
Tarsk Usecoding

Available Providers (1)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Requestymistral-medium-3-5@eu$1.65/MTok$8.25/MTok262.1K262.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output