MiniMax M3

by MiniMax

MiniMax M3 is a 427B-parameter mixture-of-experts model, with 23B active parameters. It supports text, images, and video, and has a 1,048,576-token context window. Benchmark results cover coding, tool use, and multimodal tasks.

Best for: Long-running coding agents that work with images and video.

1M context

Text
Reasoning
Tool use
Image input
Vision
Video input

Model weights

Try it in the playground

Pricing

USD per 1M tokens.

Window	Input	Cached input	Output
asap	$0.28	$0.06	$1.10

What one request costs

Prompt94Ktokens

Cached prefix66Ktokens

Reply2Ktokens

$0.0132

per request to MiniMax M3

Prompt: 59.7%
Cached: 27.9%
Reply: 12.5%

The same request, across other models