minimax-m3
ImageVoiceMultimodal
MiniMax-M3 is a multimodal foundation model that supports text, image, and video input, produces text output, and offers a 1M-token context window for long-running agents, coding, and tool use. Built on MiniMax Sparse Attention, it cuts long-context cost to about one-twentieth of the previous generation while improving prefilling and decoding speed and preserving quality on most tasks.
Oken covers 15 routes, evaluated by authenticity, token usage (Caching), and uptime against the official baseline.
6routes
0routes
0routes
3routes
8 providers and 16 routes included
Route Quality
Provider Type
Billing Method
Route Performance
Uptime
Token Usage
Platform Services
Payment Method
Supported Languages
Supported Regions
Recharge Platform
