Mistral AI

Mistral Nemo

mistralai/mistral-nemo

JSON

Specification

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

Mistral Nemo

open weights tools

Mistral AI mistralai/mistral-nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

Input $/1M: $0.02
Output $/1M: $0.03
Context: 131K
Max output: 16K
Released: Jul 19, 2024
Modalities: text

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 Nemo
targets:
  - id: mistral-nemo
    kind: llm
    name: Mistral Nemo
    metadata:
      model: mistralai/mistral-nemo          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.000025

Price among Mistral AI models

Input list price per million tokens; Mistral Nemo is the cheapest of 13 listed.

More from Mistral AI

Other models by the same vendor in the catalogue.