M
MiniMax M3 (batch)OPEN
MiniMax M3 (batch) (MiniMax): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.
Prices update automatically — checked hourly against provider list prices.
Benchmarks & performance
Independent benchmark scores for MiniMax M3 (batch), measured by Artificial Analysis. Higher is better.
For the same budget, MiniMax M3 (batch) delivers 14 times more capability. Open weights also mean you can self-host it and pay nothing per token.
About this model
MiniMax M3 (batch) is an open-weight AI model by MiniMax. You can download and self-host it for free; the prices below are hosted-API list prices, tracked hourly, for when you prefer convenience over self-hosting.
Frequently asked questions
What is MiniMax M3 (batch)?
MiniMax M3 (batch) is an AI language model from MiniMax. It is open-weight: you can download it and run it on your own hardware, for free. It scores 44.4 on the Artificial Analysis intelligence index.
Is MiniMax M3 (batch) free?
The weights are free and open — you can self-host MiniMax M3 (batch) and pay nothing per token. If you prefer a hosted API, list prices are $0.15 per million input tokens and $0.6 per million output tokens.
What is MiniMax M3 (batch) good at?
Independent benchmarks from Artificial Analysis give it GPQA 92.9%, Humanity's Last Exam 37.1%, Long Context Reasoning 74%, SciCode 45.4%, IFBench 82.9%, τ²-Bench 88.9%, τ-Bench Banking 13%, Terminal-Bench 65.2%, Terminal-Bench Hard 42.4%. It is particularly used for code generation.
How fast is MiniMax M3 (batch)?
It generates about 96.6 tokens per second, with a median 1.72s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host MiniMax M3 (batch)?
Yes. MiniMax M3 (batch) has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.