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
#328
Up 204% week over week
Tokens
144.6M
2026-08-14
Requests
24.6K
24,554
Tool calls
-
Input / M
$0.15
Output / M
$0.60
Cache / M
$0.03
Context
524K
524,288 tokens