Mistral: Ministral 3 3B 2512

Image input Text input Text output
Author's Description

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

Key Specifications
Cost
$$
Context
131K
Parameters
3B
Released
Dec 02, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Max Tokens Temperature Top P Response Format Frequency Penalty Presence Penalty Structured Outputs Tools Seed Tool Choice
Features

This model supports the following features:

Tools Response Format Structured Outputs
Performance Summary

Mistral: Ministral 3 3B 2512, the smallest model in the Ministral 3 family, demonstrates exceptional performance across several key metrics. It consistently ranks among the fastest models, achieving an Infinityth percentile in speed across all 8 benchmarks. Similarly, its pricing is highly competitive, also securing an Infinityth percentile ranking across all benchmarks. The model exhibits outstanding reliability with a 99% success rate, indicating minimal technical failures. In terms of specific benchmarks, Ministral 3 3B shows a notable strength in General Knowledge (94.0% accuracy) and Ethics (98.0% accuracy), performing well in these areas. It also excels in Mathematics (82.0% accuracy) and Email Classification (95.0% accuracy), where it is highlighted as the most accurate among models of comparable speed. However, the model struggles significantly with Hallucinations, achieving 0.0% accuracy, indicating it does not appropriately acknowledge uncertainty. Its performance in Instruction Following (33.0% accuracy) and Reasoning (22.0% accuracy) is also a notable weakness, suggesting limitations in handling complex, multi-step directives and abstract problem-solving. Coding performance is moderate at 78.0% accuracy. Overall, Ministral 3 3B is a highly efficient and cost-effective model, particularly strong in factual recall and classification, but requires improvement in areas demanding nuanced understanding and complex reasoning.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.1
Completion $0.1

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Mistral
Mistral | mistralai/ministral-3b-2512 131K $0.1 / 1M tokens $0.1 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by mistralai