Mistral AI

Mistral Large

mistralai/mistral-large

JSON

Specification

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

Mistral Large

tools

Mistral AI mistralai/mistral-large

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

Input $/1M: $2.00
Output $/1M: $6.00
Context: 128K
Max output: 102K
Released: Feb 26, 2024
Modalities: textfile

Cached input reads $0.20 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
targets:
  - id: mistral-large
    kind: llm
    name: Mistral Large
    metadata:
      model: mistralai/mistral-large          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 128000
    cost:
      usd_per_1k_tokens: 0.004000

Price among Mistral AI models

Input list price per million tokens; Mistral Large is the most expensive of 13 listed.

More from Mistral AI

Other models by the same vendor in the catalogue.