Mistral AI

Mistral Small 3.2 24B

mistralai/mistral-small-3.2-24b-instruct

JSON

Specification

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

Mistral Small 3.2 24B

open weights tools

Mistral AI mistralai/mistral-small-3.2-24b-instruct

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

Input $/1M: $0.07
Output $/1M: $0.20
Context: 131K
Max output: 16K
Released: Jun 20, 2025
Modalities: imagetext

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 Small 3.2 24B
targets:
  - id: mistral-small-3-2-24b-instruct
    kind: llm
    name: Mistral Small 3.2 24B
    metadata:
      model: mistralai/mistral-small-3.2-24b-instruct          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.000138

Price among Mistral AI models

Input list price per million tokens; Mistral Small 3.2 24B is the cheapest of 13 listed.

More from Mistral AI

Other models by the same vendor in the catalogue.