Mistral AI

Ministral 3 14B

Generally availableOpen weights262K context

Summary

Ministral 3 14B is an open-weight language model from Mistral AI, released on 2 Dec 2025. It accepts text, images and PDFs and generates text, with a 262K-token context window and up to 262K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.20 per million input tokens and $0.20 per million output tokens (Mistral API), across 3 providers we track.

Open vision-language model for efficient local deployment, instruction following, and tool use

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMistral AI
Release date2 Dec 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters13.9B [Hugging Face]
Context window262K (262,144 tokens) [models.dev]
Max output262K tokens [models.dev]
Knowledge cutoffDec 2024 [models.dev]
InputText, images and PDFs [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facemistralai/Ministral-3-14B-Instruct-2512 [Hugging Face]

Ministral 3 14B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Mistral API
ministral-14b-2512
$0.20$0.20$0.02262Kmodels.dev, 18 Nov 2026
Amazon Bedrock
mistral.ministral-3-14b-instruct
$0.20$0.20–128Kmodels.dev, 18 Nov 2026
OpenRouter
mistralai/ministral-14b-2512
$0.20$0.20$0.02262KOpenRouter, 18 Nov 2026

Running Ministral 3 14B locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)8.5 GB11 GB15 GB
Q8_0 (8-bit)15 GB17 GB21 GB
FP16 / BF16 (16-bit)28 GB30 GB34 GB

At 4-bit with an 8K conversation, Ministral 3 14B needs about 11 GB, so it fits on a graphics card with 12 GB or more, such as the NVIDIA GeForce RTX 3060 12 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.

Frequently asked questions

What is the context window of Ministral 3 14B?

Ministral 3 14B has a context window of 262,144 tokens (262K) and can generate up to 262,144 tokens in a single response, according to models.dev.

How much does the Ministral 3 14B API cost?

Through Mistral API, Ministral 3 14B costs $0.20 per million input tokens and $0.20 per million output tokens. Prices last verified 18 Nov 2026.

Is Ministral 3 14B open source?

Ministral 3 14B is an open-weight model: its weights are published on Hugging Face as mistralai/Ministral-3-14B-Instruct-2512 under the apache-2.0 license. Check the license terms before commercial use.

When was Ministral 3 14B released?

Mistral AI released Ministral 3 14B on 2 Dec 2025, according to models.dev.

Which providers offer Ministral 3 14B?

We track Ministral 3 14B on 3 providers: Mistral API, Amazon Bedrock, OpenRouter.

How much VRAM does Ministral 3 14B need?

About 11 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 17 GB at 8-bit. The 4-bit model fits on a graphics card with 12 GB or more, such as the NVIDIA GeForce RTX 3060 12 GB. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Step 3.5 FlashStepFun29 Jan 2026262K$0.10$0.30Open
NVIDIA Nemotron Nano 3 30BNVIDIA15 Dec 2025262K$0.05$0.20Open
Jamba MiniAI21 Labs8 Jan 2026256K$0.20$0.40Open
GLM-4.7-FlashXZhipu AI (Z.ai)19 Jan 2026200K$0.06$0.40Open
GLM-4.7-FlashZhipu AI (Z.ai)19 Jan 2026200K$0.06$0.40Open
NVIDIA Nemotron 3 Super 120B A12BNVIDIA11 Mar 2026262K$0.07$0.40Open

Change history

  • Parameter count changed from 13.9B to 13.9B
  • Knowledge cutoff changed from none to Dec 2024
  • Input modalities changed from text, image to text, image, pdf
  • Now listed on Mistral API
  • Context window changed from 128K to 262K
  • Max output changed from 4K to 262K
  • Name changed from Ministral 14B 3.0 to Ministral 3 14B

Sources