AI KNOWLEDGE DESK

Models · entities · concepts · comparisons · practical tools

GETLLMS.ORG

🚀Function Overview

Mistral Large 4 accepts text and images and returns text. Use mistral-large-4 on the hosted API or the released mistralai/Mistral-Large-4-1T-A52B checkpoint; deployment and licensing conditions differ.

Key Features

  • API ID mistral-large-4; Public Preview
  • 1M context; maximum output not confirmed here
  • Model card: about 1T total, 49B active per token; 52B including embedding/output layers.
  • Multimodal input; exact media preprocessing follows the provider contract
  • Structured outputs, function calling, batching and agent/conversation APIs
  • Released FP8 and NVFP4 weights; Mistral Ecosystem Open-Weight License, separate MaaS commercial license.

Use Cases

  • •Trial a multimodal API for document and coding tasks.
  • •Evaluate structured outputs and tool use with a defined harness.
  • •Evaluate self-managed inference with released checkpoints, actual hardware requirements and license terms.

⚙️Input Parameters

model

string

mistral-large-4

messages

array

Chat payload using the current Mistral multimodal input schema.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "mistral-large-4",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the supplied document and identify uncertain claims."
    }
  ]
}

Output Results

Illustrative API request, not an executed preview test.

Quick Actions

Technical Specifications

Hardware Type
Hosted API Public Preview / self-managed official FP8 or NVFP4 checkpoint
Commercial Use
Model card: commercial/non-commercial use under Mistral Ecosystem Open-Weight License; Model-as-a-Service business requires separate commercial license.
Pricing
Hosted USD per 1M tokens: $0.70 input, $0.07 cached, $2.10 output, checked November 4, 2026. Self-managed compute and any required MaaS license are separate.