MiniMax-M3 by MiniMax (minimax.io) | AI model information

Loading models

Subscribe

Follow catalog updates and new guides

Open RSS feed Medium guides

RSS covers catalog changes. Medium covers how-to guides and write-ups.

MiniMax-M3 by MiniMax (minimax.io) | AI model information

Get 10-25% off Discuss

Model details

MiniMax-M3

Loading model overview

MiniMax (minimax.io)MiniMax-M3minimax

Open provider page Provider docs

Quick Info

Provider: MiniMax (minimax.io)
Model key: MiniMax-M3
Release date: Jun 1, 2026
Last updated: Jun 1, 2026

Cost

Input token cost: $0.60
Output token cost: $2.40

Limits

Output tokens: 128,000 tokens
Context window

Latest news about MiniMax-M3

Videos about MiniMax-M3

Recent tweets and retweets from MiniMax (minimax.io)

More models around MiniMax-M3

Also served by

This exact model name is also listed by 4 other providers.

MiniMax (minimaxi.com)MiniMax Token Plan (minimax.io)MiniMax Token Plan (minimaxi.com)OpenRouter

37 providers

Currently listed through these providers:

MiniMax (minimax.io)Alibaba (China)Alibaba Coding Plan Alibaba Coding Plan (China)Alibaba Token Plan +32 more

25 providers

Currently listed through these providers:

MiniMax (minimax.io)AIHubMix Alibaba (China)Auriko Cortecs +20 more

10 providers

MiniMax-M2.7-highspeed

Currently listed through these providers:

MiniMax (minimax.io)Auriko LLM Gateway Merge Gateway MiniMax (minimaxi.com)+5 more

8 providers

MiniMax-M2.5-highspeed

Currently listed through these providers:

MiniMax (minimax.io)LLM Gateway Merge Gateway MiniMax (minimaxi.com)MiniMax Token Plan (minimax.io)+3 more

3 providers

Currently listed through these providers:

Amazon Bedrock Jiekou.AI Meganova

2 providers

Currently listed through these providers:

NanoGPT OpenRouter

1 provider

Coding MiniMax M2.7

Currently listed through:

1 provider

Coding MiniMax M2.7 Highspeed

Currently listed through:

1 provider

MiniMax M2.7 High Speed

Currently listed through:

Vercel AI Gateway

1 provider

Currently listed through:

1 provider

MiniMax M2.5 TEE

Currently listed through:

1 provider

MiniMaxAI/MiniMax-M2.5

Currently listed through:

Discuss this model

Powered byHyvor Talk

Add corrections, implementation notes, pricing changes, or usage caveats for other readers.

Input modalities

Output modalities

Capabilities

512,000 tokens

Recent tweets and retweets from MiniMax (minimax.io)

Jun 1, 2026, 12:39 PMUTC

Looking good 👀 Historically MiniMax models have worked well in OpenHands, looking forward to giving this one a whirl!

Jun 2, 2026, 11:08 PMUTC

MiniMax M3 now on GMI Cloud @gmi_cloud

Jun 2, 2026, 10:53 PMUTC

Try MiniMax-M3 today -> platform.minimax.io

Jun 2, 2026, 10:53 PMUTC

We wrapped a live session on M3 yesterday with the @togethercompute team & our researchers @zpysky1125 and @HaohaiSun A few highlights 🧵 1. MSA (MiniMax Sparse Attention) is the star ⭐️. Unlike CSA/HCA, which compress the KV cache, MSA keeps the real, uncompressed KV and…

Jun 2, 2026, 10:20 PMUTC

MiniMax-M3 #6 overall on @ValsAI the new open-weight SOTA 🚀