PreviewChat Models

Mistral AI

Mistral Large 4

Mistral’s newest flagship is an open-weight multimodal model in v26.10 preview, with 1M context, vision, function calling, and structured output.

1M contextVisionFunction callingStructured output

At a glance

Know the model before you prompt.

Mistral AI specifications
Context window
1M tokens
Maximum output
64K tokens
Inputs → output
Text + Images → Text

Capabilities & boundaries

What it supports. Where the limits are.

Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.

Supported API features and tools

  • Open-weight multimodal model with vision
  • Function calling
  • Structured output
  • Training data up to 2026

Before you choose

  • Mistral Large 4 is a v26.10 preview.

Put it to work

Start with a more useful prompt.

Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.

Workflow 01

Extract fields from a photographed form

Supply the photo and the fields you want returned.

Read the attached form and return a JSON object with the fields listed below. Use null for unreadable fields and include the original wording for each field you can verify.

Common questions

A few things worth knowing.

Is Mistral Large 4 open-weight?

Yes. Mistral Large 4 is an open-weight multimodal model in v26.10 preview.

Does Mistral Large 4 support function calling?

Yes. It supports function calling and structured output.

Same provider