Mistral: Mistral Medium 3.5 (batch)
by Mistral AItext+image+file->text1 endpoint
Overview
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.
Capabilities
Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Long context
File input
Top-P sampling
Stop sequences
Deterministic seed
Modalities
Input
TextImageFile
Output
Text
Technical Specifications
Context Window
262.1K tokens
Max Output
209.7K tokens
Tokenizer
Mistral
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p