Context
524K
Input
$0.28/M
Output
$1.10/M
Aliases:minimax-m3.0
MiniMax's natively multimodal flagship with a 1M-token context window powered by MiniMax Sparse Attention (MSA). Supports image and PDF input, toggleable thinking, strong agentic tool calling, and long-context reasoning.
deepinfra/minimax-m3Quantfp8
- Input
- $0.28/M
- Output
- $1.10/M
- Context
- 524K
- Max out
- 512K
- Cache read
- $0.06/M
- Cache write
- $0.28/M
- Thinking out
- $1.10/M
Priority / Fast