Enterprise DNAEnterprise DNA
LModelsBest vision
Mistral logo

Ministral 3 3B 2512

by Mistral

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

M3

Models

Ministral 3 3B 2512

Added 10 July 2026

#mistralai

Overview

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

How to use / API access

Call via OpenRouter with model id `mistralai/ministral-3b-2512`.

  • openrouter · mistralai/ministral-3b-2512 Docs

OpenRouter id: mistralai/ministral-3b-2512

Benchmarks

  • Intelligence Index (artificial-analysis): 4.8 index
  • Coding Index (artificial-analysis): 4.8 index
  • Agentic Index (artificial-analysis): 0.8 index
  • Design Arena 3d (other): 963 elo · #117
  • Design Arena codecategories (other): 1012 elo · #121
  • Design Arena gamedev (other): 950 elo · #128
  • Design Arena website (other): 1029 elo · #123

Notes

Ministral 3 3B 2512 is listed in the EDNA Models directory from the OpenRouter catalogue.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

USAGE / OPENROUTER

How much Ministral 3 3B 2512 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
4.4B ▼1.5%
Requests, last 7 days
4.2M
Tool calls, last 7 days
54.6K
Intelligence score
4.8
Average cost per request
0.7¢
Price per million tokens
$0.1 in · $0.1 out
0500M1B19 Sept: 266M tokens, 289K requests20 Sept: 297M tokens, 336K requests21 Sept: 484M tokens, 491K requests22 Sept: 543M tokens, 603K requests23 Sept: 480M tokens, 518K requests24 Sept: 549M tokens, 555K requests25 Sept: 635M tokens, 549K requests26 Sept: 277M tokens, 321K requests27 Sept: 353M tokens, 446K requests28 Sept: 511M tokens, 581K requests29 Sept: 540M tokens, 571K requests30 Sept: 487M tokens, 555K requests1 Oct: 457M tokens, 504K requests2 Oct: 456M tokens, 445K requests3 Oct: 328M tokens, 352K requests4 Oct: 419M tokens, 479K requests5 Oct: 594M tokens, 665K requests6 Oct: 669M tokens, 717K requests7 Oct: 707M tokens, 686K requests8 Oct: 812M tokens, 766K requests9 Oct: 736M tokens, 555K requests10 Oct: 504M tokens, 432K requests11 Oct: 422M tokens, 494K requests12 Oct: 560M tokens, 611K requests13 Oct: 743M tokens, 727K requests14 Oct: 713M tokens, 702K requests15 Oct: 717M tokens, 714K requests16 Oct: 523M tokens, 458K requests17 Oct: 413M tokens, 376K requests18 Oct: 710M tokens, 597K requests19 Sept3 Oct17 Oct18 OctSee where it ranks on the leaderboard →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Check the source

Price date: 2026-10-18. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 4.8 (2026-10-18) ↗Coding Index: 4.8 (2026-10-18) ↗Agentic Index: 0.8 (2026-10-18) ↗
Compare this model with alternatives →