MiniMax M3
MiniMaxminimax-m3
Released Jun 1, 2026
Providers
5
Context
1.0M
Input
$0.28/M
Output
$1.10/M
BAA-eligible on 1 of 5 providersPHI requires a signed BAA from Concentrate and HIPAA-enabled organization.
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.
minimax/minimax-m3QuantUnspecified
- Input
- $0.30/M
- Output
- $1.20/M
- Context
- 1.0M
- Max out
- 524K
- Cache read
- $0.06/M
- Cache write
- $0.30/M
- Thinking out
- $1.20/M
FlexPriority / Fast
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
fireworks/minimax-m3QuantUnspecified
- Input
- $0.30/M
- Output
- $1.20/M
- Context
- 512K
- Max out
- 128K
- Cache read
- $0.06/M
- Cache write
- $0.30/M
- Thinking out
- $1.20/M
Flex
nebius/minimax-m3Quantfp4
- Input
- $0.30/M
- Output
- $1.20/M
- Context
- 1.0M
- Max out
- 524K
- Caching
- Not offered
- Thinking out
- $1.20/M
FlexPriority / Fast
novita/minimax-m3Quantfp8
- Input
- $0.30/M
- Output
- $1.20/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.06/M
- Cache write
- $0.30/M
- Thinking out
- $1.20/M
FlexPriority / Fast