Mistral AI

Mistral Small 3

mistralai/mistral-small-24b-instruct-2501

JSON

Specification

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

Mistral Small 3

open weights

Mistral AI mistralai/mistral-small-24b-instruct-2501

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

Input $/1M: $0.05
Output $/1M: $0.08
Context: 33K
Max output: 16K
Released: Jan 30, 2025
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 Small 3
targets:
  - id: mistral-small-24b-instruct-2501
    kind: llm
    name: Mistral Small 3
    metadata:
      model: mistralai/mistral-small-24b-instruct-2501          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: false
      context_window: 32768
    cost:
      usd_per_1k_tokens: 0.000065

Price among Mistral AI models

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

More from Mistral AI

Other models by the same vendor in the catalogue.