minimax-m2

by Minimax

MiniMax-M2 redefines efficiency for intelligent agents. It is a compact, fast, and cost-effective MoE model with a total of 230 billion parameters and 10 billion active parameters, designed for top performance in coding and intelligent agent tasks while maintaining strong general intelligence. With only 10 billion active parameters, MiniMax-M2 delivers the complex end-to-end tool usage performance expected from today's leading models, but in a more streamlined form factor, making deployment and scaling easier than ever before.

API Pricing

Input$0.29 / 1M tokens
Output$1.15 / 1M tokens

Specifications

Context window204,800 tokens
Modalitiestext
Featuresthinking, tool calling, function calling, structured outputs

FAQ

What is minimax-m2?

MiniMax-M2 redefines efficiency for intelligent agents. It is a compact, fast, and cost-effective MoE model with a total of 230 billion parameters and 10 billion active parameters, designed for top performance in coding and intelligent agent tasks while maintaining strong general intelligence. With only 10 billion active parameters, MiniMax-M2 delivers the complex end-to-end tool usage performance expected from today's leading models, but in a more streamlined form factor, making deployment and scaling easier than ever before.

What is the context length of minimax-m2?

minimax-m2 has a 204,800 token context window.

How much does minimax-m2 cost?

On AIHubMix, minimax-m2 costs $0.29 per million input tokens and $1.15 per million output tokens.

What modalities does minimax-m2 support?

minimax-m2 accepts text input.

What features does minimax-m2 support?

minimax-m2 supports thinking, tool calling, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.

How do I call minimax-m2 via API?

minimax-m2 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to minimax-m2 — no other code changes needed.

Who develops minimax-m2?

minimax-m2 is developed by Minimax. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More from Minimax

minimax-h3

by Minimax

MiniMax H3 is an open, general-purpose multimodal video model provided by MiniMax that…

$2/1M in · $2/1M out

minimax-m3

by Minimax

The MiniMax M3 is a flagship programming model built for real-world productivity. As a…

$0.29/1M in · $1.15/1M out
204,800 tokens context

coding-minimax-m3-free

by Minimax

coding-minimax-m3-free is a free and open version offered by AIHubMix specifically for…

204,800 tokens context

coding-minimax-m2.7-free

by Minimax

coding-minimax-m2.7-free is a free and open version offered by AIHubMix specifically for…

204,800 tokens context

minimax-m2.7

by Minimax

MiniMax M2.7 can autonomously build complex Agent Harnesses and, leveraging capabilities…

$0.3/1M in · $1.18/1M out
200,000 tokens context

coding-minimax-m2.5-free

by Minimax

coding-minimax-m2.5-free is a free and open version offered by AIHubMix specifically for…

204,800 tokens context

Use minimax-m2 via the AIHubMix unified API — one interface for every major LLM.