Mistral AI

Ministral 3 14B 2512

mistralai/ministral-14b-2512

JSON

Specification

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

Ministral 3 14B 2512

open weights tools

Mistral AI mistralai/ministral-14b-2512

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

Input $/1M: $0.20
Output $/1M: $0.20
Context: 262K
Max output: 210K
Released: Dec 2, 2025
Modalities: textimage

Intelligence index-

Coding index14

Agentic index-

Cached input reads $0.02 per 1M · weights on Hugging Face as mistralai/Ministral-3-14B-Instruct-2512

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 Ministral 3 14B 2512
targets:
  - id: ministral-14b-2512
    kind: llm
    name: Ministral 3 14B 2512
    metadata:
      model: mistralai/ministral-14b-2512          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 262144
    cost:
      usd_per_1k_tokens: 0.000200

Price among Mistral AI models

Input list price per million tokens; Ministral 3 14B 2512 is the 6th cheapest of 13 listed.

More from Mistral AI

Other models by the same vendor in the catalogue.