Mistral AI

Mistral Medium 3

mistralai/mistral-medium-3

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Mistral Medium 3

tools

Mistral AI mistralai/mistral-medium-3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

Input $/1M: $0.40
Output $/1M: $2.00
Context: 131K
Max output: 105K
Released: May 7, 2025
Modalities: textimagefile

Cached input reads $0.04 per 1M

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Mistral Medium 3
targets:
  - id: mistral-medium-3
    kind: llm
    name: Mistral Medium 3
    metadata:
      model: mistralai/mistral-medium-3          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.001200

Price among Mistral AI models

Input list price per million tokens; Mistral Medium 3 is the 8th cheapest of 13 listed.

More from Mistral AI

Other models by the same vendor in the catalogue.