Mistral AI: Mistral Medium 3.1

Coming soonQuick Start

Mistral Medium 3.1 is Mistral AI's mid-size enterprise model, released 2025-08, an update to Mistral Medium 3 that targets strong reasoning and multimodal performance at lower operational cost. It is built for coding, STEM work, and enterprise adaptation, and its accuracy is competitive with larger models such as Claude Sonnet 3.7 and Llama 4 Maverick.

This model is not routed on MirAPI yet — prices shown are the official list prices. Create an account to get notified when it goes live.

Modalities
inTextinImageinFileoutText
Price / 1M
$0.40 / $2.00
Context
131K
Knowledge cutoff
2025-06-30

Capabilities

VisionTool usePrompt cachingStructured output

Benchmarks

bar = score (0–100) · ▏ median

Scores from vendor reports and public leaderboards. No private evals.

Intelligence Index
General ability
14.7
#73
Coding Index
Code
20.5
#74
Agentic Index
Agentic
6.1
#64

Showcase

Three fixed prompts, identical for every chat model. Outputs are archived verbatim — copy the prompt to reproduce.

Task prompt · identical for all models
Build a single-file HTML page using three.js from a CDN: a low-poly planet with a tilted ring of ~200 orbiting particles, a soft key light plus rim light, slow auto-rotation, and drag-to-orbit controls. No build tools — one file only.
Archived output
Archive not published yet

Every model will run this exact prompt; the output lands here verbatim, with tokens and per-run cost.

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="mistralai/mistral-medium-3.1",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire Mistral Medium 3.1 into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free