Mistral AI

Mistral: Ministral 3 3B 2512

by Mistral AItext+image->text3 endpoints

Overview

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed

Modalities

Input
TextImage
Output
Text

Technical Specifications

Context Window
131.1K tokens
Max Output
104.9K tokens
Tokenizer
Mistral
Uptime (24h)
9990.9%

Supported Parameters

frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Pricing

Per 1M tokens
Input$0.10
Output$0.10
Cache read$0.01
Added
December 2, 2025
Last synced 9/18/2026