MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Rank
#6
Up 95% week over week
Tokens
5.02T
2026-09-06
Requests
66.5M
66,522,949
Tool calls
-
Input / M
Free
Output / M
Free
Cache / M
Free
Context
1.0M
1,048,576 tokens