Mistral AI

Ministral 3 8B

Generally availableOpen weights262K context

Summary

Ministral 3 8B 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 $0.15 per million input tokens and $0.15 per million output tokens (Mistral API), across 3 providers we track.

Compact open vision-language model for edge 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]
Parameters8.9B [Hugging Face]
Context window262K (262,144 tokens) [models.dev]
Max output262K tokens [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-3-8B-Instruct-2512 [Hugging Face]

Ministral 3 8B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Mistral API
ministral-8b-2512
$0.15$0.15$0.01262Kmodels.dev, 18 Nov 2026
Amazon Bedrock
mistral.ministral-3-8b-instruct
$0.15$0.15–128Kmodels.dev, 18 Nov 2026
OpenRouter
mistralai/ministral-8b-2512
$0.15$0.15$0.01262KOpenRouter, 18 Nov 2026

Running Ministral 3 8B 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)5.4 GB7.3 GB11 GB
Q8_0 (8-bit)9.5 GB11 GB15 GB
FP16 / BF16 (16-bit)18 GB20 GB23 GB

At 4-bit with an 8K conversation, Ministral 3 8B needs about 7.3 GB, so it fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 GB. Check your own hardware, or see Running local LLMs on an 8 GB GPU on our sister site AIPCs.

Frequently asked questions

What is the context window of Ministral 3 8B?

Ministral 3 8B 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 8B API cost?

Through Mistral API, Ministral 3 8B costs $0.15 per million input tokens and $0.15 per million output tokens. Prices last verified 18 Nov 2026.

Is Ministral 3 8B open source?

Ministral 3 8B is an open-weight model: its weights are published on Hugging Face as mistralai/Ministral-3-8B-Instruct-2512 under the apache-2.0 license. Check the license terms before commercial use.

When was Ministral 3 8B released?

Mistral AI released Ministral 3 8B on 2 Dec 2025, according to models.dev.

Which providers offer Ministral 3 8B?

We track Ministral 3 8B on 3 providers: Mistral API, Amazon Bedrock, OpenRouter.

How much VRAM does Ministral 3 8B need?

About 7.3 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 11 GB at 8-bit. The 4-bit model fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 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
NVIDIA Nemotron Nano 3 30BNVIDIA15 Dec 2025262K$0.05$0.20Open
Step 3.5 FlashStepFun29 Jan 2026262K$0.10$0.30Open
Qwen/Qwen3.5-9BAlibaba (Qwen)23 Feb 2026262K$0.10$0.15Open
Jamba MiniAI21 Labs8 Jan 2026256K$0.20$0.40Open
Gemma 4 26B A4B ITGoogle DeepMind2 Apr 2026262K$0.07$0.30Open
GLM-4.7-FlashXZhipu AI (Z.ai)19 Jan 2026200K$0.06$0.40Open

Change history

  • Parameter count changed from 8.9B to 8.9B
  • Input modalities changed from text, image to text, image, pdf
  • Context window changed from 128K to 262K
  • Max output changed from 4K to 262K
  • Now listed on Mistral API

Sources