Roar AI
DiscordGet started
All models
MiniMax · Open weights

MiniMax-M3

MiniMax-M3 costs $0.39 per million input tokens and $1.56 per million output tokens on Roar AI. MiniMax’s open flagship, with strong coding, a million-token context and image and video input.

Input$0.39per 1M tokens
Output$1.56per 1M tokens
Context window1.05Mtokens

MiniMax-M3 API pricing

Input$0.39 per 1M tokens
Output$1.56 per 1M tokens
Cached input$0.078 per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $2.73. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

Made byMiniMax
ReleasedJune 2026
TypeChat
Context window1.05M tokens
ReadsText, images, video
Thinks before answeringYes, adjustable
WeightsOpen (MiniMax community licence)
SizeAbout 428B total, 23B active
Processed inGlobal
Model idminimax-m3

About MiniMax-M3

MiniMax-M3 was pitched as the first open model to combine frontier-level coding, a million-token context and native image and video input. MiniMax reports 59.0% on SWE-bench Pro and 80.5% on SWE-bench Verified, and says its new attention design makes it many times faster than M2 at full context length.

You can leave thinking on, switch it off, or let the model decide per request, which is the default. That makes it flexible for agents that mix quick calls with hard ones, such as a coding agent reading screenshots.

What is MiniMax-M3 good for?

  • Coding agents that read screenshots or screen recordings.
  • Long documents mixed with images and video.
  • Calls where latency matters, with thinking switched off.

MiniMax-M3 limitations

  • MiniMax’s licence restricts some commercial uses.
  • Its scores are MiniMax’s own.

How to use the MiniMax-M3 API

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="minimax-m3",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

MiniMax-M3 FAQ

How much does MiniMax-M3 cost?

Input is $0.39 per 1M tokens; output is $1.56 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $2.73.

Can I use MiniMax-M3 alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from MiniMax-M3 to another model only means changing the model name in your code.

Is MiniMax-M3 open source?

Its weights are open under the MiniMax community licence licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.

What is the context window of MiniMax-M3?

MiniMax-M3 can read up to 1.05M tokens in one request.

Can MiniMax-M3 read images and PDFs?

It reads images directly. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge.

Start using MiniMax-M3

Create a free account, get an API key and call MiniMax-M3 with the OpenAI SDK.