Mistral: Ministral 3 14B 2512

Text input Image input Text output
Author's Description

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

Key Specifications
Cost
$$
Context
262K
Parameters
14B
Released
Dec 02, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

This model supports the following features:

Structured Outputs Response Format Tools
Performance Summary

Mistral: Ministral 3 14B 2512, the largest in its family, demonstrates exceptional operational efficiency, consistently ranking among the fastest models and offering highly competitive pricing across all benchmarks. Its reliability is outstanding, achieving a 100% success rate with no technical failures. In terms of capabilities, the model exhibits strong performance in General Knowledge (98.5% accuracy) and Ethics (99.0% accuracy), placing it in the 56th and 58th percentiles respectively. It also performs well in Email Classification (98.0% accuracy) and Coding (87.0% accuracy). A notable strength is its complete absence of hallucinations, scoring 0.0% accuracy on the Hallucinations benchmark by correctly identifying fictional concepts. However, the model shows weaknesses in more complex cognitive tasks. Its accuracy in Mathematics (81.0%), Instruction Following (52.0%), and Reasoning (52.0%) falls into the lower percentiles, suggesting areas for improvement in advanced problem-solving and multi-step instruction adherence. Despite these areas, its overall efficiency and strong performance in core knowledge and ethical understanding make it a powerful and cost-effective language model with vision capabilities.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.35
Completion $0.35

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Mistral
Mistral | mistralai/ministral-14b-2512 262K $0.2 / 1M tokens $0.2 / 1M tokens
Together
Together | mistralai/ministral-14b-2512 262K $0.2 / 1M tokens $0.2 / 1M tokens
NextBit
NextBit | mistralai/ministral-14b-2512 262K $0.35 / 1M tokens $0.35 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by mistralai