minimax-m2.5-highspeed · Minimax
• Same performance as minimax-m2.5 • Significantly faster inference
• Same performance as minimax-m2.5 • Significantly faster inference
MiniMax M2.5 Highspeed has a 204,800 token context window.
On AIHubMix, MiniMax M2.5 Highspeed costs $0.288 per million input tokens and $1.152 per million output tokens.
MiniMax M2.5 Highspeed accepts text input.
MiniMax M2.5 Highspeed supports thinking, tool calling, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.
MiniMax M2.5 Highspeed 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-m2.5-highspeed — no other code changes needed.
MiniMax M2.5 Highspeed is developed by Minimax. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
MiniMax M2.5 Highspeed was released on February 13, 2026 by Minimax.
MiniMax H3 (minimax-h3) is a general-purpose omni-modal generation model developed by the…
Developed by Minimax, MiniMax-M2.7 is a next-generation large language model designed for…
MiniMax H3 (minimax-h3) is a general-purpose omni-modal generation model developed by the…
The MiniMax M3 is a flagship programming model built for real-world productivity. As a…
coding-minimax-m3-free is a free and open version offered by AIHubMix specifically for…
coding-minimax-m2.7-free is a free and open version offered by AIHubMix specifically for…
Use MiniMax M2.5 Highspeed via the AIHubMix unified API — one interface for every major LLM.