Ministral 3 3B 2512

Provider: Mistral AI EU Official API price

Input price
$0.10
/ 1M tokens
Output price
$0.10
/ 1M tokens
Cache price
$0.01
/ 1M tokens (read)
Context
131K tokens
Max output 105K tokens

Overview

Mistral AI's Ministral 3 3B 2512 is a versatile mid-tier model designed for multimodal and structured data workloads. It offers advanced capabilities like vision and function-calling, coupled with a substantial context window. This model is suitable for developers seeking robust functionality at a competitive price point.

Strengths

  • Native vision capabilities for processing image and text inputs effectively.
  • Robust function-calling support to integrate with external tools and services.
  • Reliable JSON mode for generating structured and easily parseable outputs.
  • Expansive 131072-token context window suitable for long documents and complex conversations.
  • Symmetric input and output pricing at a consistent $0.10 per million tokens.
  • Highly cost-effective cache reads available at only $0.01 per million tokens.

Best use cases

  • Analyzing image content alongside text for enhanced understanding in various applications.
  • Orchestrating complex workflows by integrating with APIs through function calls.
  • Summarizing or extracting detailed information from very long text documents or codebases.
  • Generating structured data outputs in JSON format for automated processing and data pipelines.
  • Building applications requiring efficient retrieval of frequently accessed information via caching.

Pricing position

Ministral 3 3B 2512 is priced at $0.10/M tokens for both input and output, positioning it above Mistral Nemo ($0.02/$0.03 per M) and Mistral Small 3 ($0.05/$0.08 per M). However, its output price is notably lower than Mistral Small 3.2 24B ($0.20/M), Voxtral Small 24B 2507 ($0.30/M), and Devstral Small 1.1 ($0.30/M). Compared to similarly priced peers like Gemini Flash Lite and GPT-4.1 Nano, Ministral 3 3B 2512 offers a significantly lower output price of $0.10/M, contrasting with their typical $0.40/M output costs.

Caveats

The maximum output token limit for Ministral 3 3B 2512 is currently unknown, which could impact use cases requiring very lengthy responses. There is no free tier available for experimentation or low-volume usage. For purely text-based tasks or applications with smaller context needs, other Mistral AI models such as Mistral Nemo or Mistral Small 3 might offer more cost-effective solutions.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
105K tokens
Listed on OpenRouter
2025-12-02
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputFunction callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.02
1M (small app) 1 0.5 $0.15
10M (mid scale) 10 5 $1.50
100M (large) 100 50 $15.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Mistral AI

Similar-priced models

Source: OpenRouter API (mistralai/ministral-3b-2512)