Mistral AI

Ministral 3B

Generally availableOpen weights128K context

Summary

Ministral 3B is an open-weight language model from Mistral AI, released on 22 Oct 2024. It accepts text and generates text, with a 128K-token context window and up to 8K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.04 per million input tokens and $0.04 per million output tokens (Azure AI Foundry), across 2 providers we track.

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Last verified 4 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperMistral AI
Release date22 Oct 2024 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window128K (128,000 tokens) [models.dev]
Max output8K tokens [models.dev]
Knowledge cutoffMar 2024 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]

Ministral 3B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Azure AI Foundry
ministral-3b
$0.04$0.04–128Kmodels.dev, 4 Oct 2026
Vercel AI Gateway
mistral/ministral-3b
$0.04$0.04–128Kmodels.dev, 4 Oct 2026

Frequently asked questions

What is the context window of Ministral 3B?

Ministral 3B has a context window of 128,000 tokens (128K) and can generate up to 8,192 tokens in a single response, according to models.dev.

How much does the Ministral 3B API cost?

Ministral 3B is listed from $0.04 per million input tokens and $0.04 per million output tokens (Azure AI Foundry). Prices last verified 4 Oct 2026.

Is Ministral 3B open source?

Ministral 3B is an open-weight model. Check the license terms before commercial use.

When was Ministral 3B released?

Mistral AI released Ministral 3B on 22 Oct 2024, according to models.dev.

Which providers offer Ministral 3B?

We track Ministral 3B on 2 providers: Azure AI Foundry, Vercel AI Gateway.

Change history

No changes detected since we started tracking this model. We re-check every source daily.

Sources