MiniMax M3
MiniMax M3 is a general-purpose chat-tuned model. Available via MiniMax. 1,048,576-token context. Efficient pricing.
MiniMax M3 is a multimodal AI model from MiniMax. It costs $0.3000 per million input tokens and $1.20 per million output tokens (blended $0.5700/M), with a 1,048,576-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
From OpenRouter's listing, read on 17 Nov 2026.
- Solid general chat performance
- Reasonable instruction following
- Multimodal: handles images alongside text
- General chat
- Drafting and rewriting
- Personal productivity
Benchmarks
More from MiniMax
See all 5 →Frequently asked questions
How much does MiniMax M3 cost?
MiniMax M3 costs $0.3000 per million input tokens and $1.20 per million output tokens, for a blended reference rate of $0.5700 per million tokens.
What is MiniMax M3's context window?
MiniMax M3 supports up to 1,048,576 tokens of context in a single request.
What is MiniMax M3 best for?
MiniMax M3 is well suited to Solid general chat performance, Reasonable instruction following and Multimodal: handles images alongside text.
Who makes MiniMax M3?
MiniMax M3 is developed and served by MiniMax.
