Models Model details

Mistral AI

Mistral: Mistral Medium 3.5 (batch)

mistralai/mistral-medium-3-5:batch

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.

Input
$0.75

/ 1M tokens

Output
$3.75

/ 1M tokens

Context window
262.14K

tokens

Limits

Context

262,144

tokens

Max output

209,715

80% of the context window

Model facts

Author

Mistral AI

Tokenizer

Mistral

Modality

Text + Image + File -> Text

Created

Apr 30, 2026

Reasoning

Default HighHighNone

Publication status

Hugging Face: not mappedLicense: not publishedParameter count: not published

Modalities

Input · TextInput · ImageInput · FileOutput · Text

Generation controls

Frequency penaltyInclude reasoningMax tokensPresence penaltyReasoningReasoning effortResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop p

Capability scores

7
Agentic index

Better than 30% of models compared

46.9
Coding index

Better than 44% of models compared

14.2
Intelligence index

Better than 36% of models compared