MiniMax: MiniMax M3

Coming soonQuick Start

MiniMax M3 is MiniMax's multimodal foundation model, released 2026-05. It handles text, image, and video inputs with text output, and is built for long-horizon agentic work, coding, and tool use. MiniMax Sparse Attention reduces per-token compute at long context, cutting cost to roughly 1/20 of the previous generation at 1M tokens while retaining quality.

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
inTextinImageinVideooutText
Price / 1M
$0.30 / $1.20
Context
1.049M
Knowledge cutoff

Capabilities

ReasoningVisionTool useLong contextPrompt cachingStructured output

Benchmarks

bar = score (0–100) · ▏ median

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

Intelligence Index
General ability
45.4
#27
Coding Index
Code
58.6
#30
Agentic Index
Agentic
36.1
#26
GPQA Diamond
Science QA
91.2
#9
τ-bench (airline)
Agentic tool use
70.6
#49

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="minimax/minimax-m3",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire MiniMax M3 into your product

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

Start free