Mistral AI

Mistral Large 3 2512

mistralai/mistral-large-2512

JSON

Specification

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

Mistral Large 3 2512

tools

Mistral AI mistralai/mistral-large-2512

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Input $/1M: $0.50
Output $/1M: $1.50
Context: 262K
Max output: 210K
Released: Dec 1, 2025
Modalities: textimagefile

Intelligence index11

Coding index20

Agentic index3

Cached input reads $0.05 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 Large 3 2512
targets:
  - id: mistral-large-2512
    kind: llm
    name: Mistral Large 3 2512
    metadata:
      model: mistralai/mistral-large-2512          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 262144
    cost:
      usd_per_1k_tokens: 0.001000

Price among Mistral AI models

Input list price per million tokens; Mistral Large 3 2512 is the 11th cheapest of 13 listed.

More from Mistral AI

Other models by the same vendor in the catalogue.