minimax/MiniMax-M3MiniMax multimodal model for long-context coding, perception, and agent planning
minimax/MiniMax-M3| Provider | Provider model ID | Context | Input / 1M | Output / 1M | Cached / 1M | Features | All pricing |
|---|---|---|---|---|---|---|---|
 MiniMax Token Plan (minimax.io) | MiniMax-M3 | 1M | $0.000 | $0.000 | $0.000 | R T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 MiniMax Token Plan (minimaxi.com) | MiniMax-M3 | 1M | $0.000 | $0.000 | $0.000 | R T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 Nvidia | minimaxai/minimax-m3 | 1M | $0.000 | $0.000 | — | R T · | View{
"input": 0,
"output": 0
} |
 Kenari | minimax-m3 | 512K | $0.000 | $0.000 | — | R T · | View{
"input": 0,
"output": 0
} |
| MiniMax (minimax.io) | MiniMax-M3 | 1M | $0.300 | $1.200 | $0.060 | R T · | View{
"cache_read": 0.06,
"context_over_200k": {
"cache_read": 0.12,
"input": 0.6,
"output": 2.4
},
"input": 0.3,
"output": 1.2,
"tiers": [
{
"cache_read": 0.12,
"input": 0.6,
"output": 2.4,
"tier": {
"size": 512000,
"type": "context"
}
}
]
} |
 OpenRouter | minimax/minimax-m3 | 1.04858M | $0.300 | $1.200 | $0.060 | R T S | View{
"cache_read": 0.06,
"input": 0.3,
"output": 1.2
} |
 Hugging Face | MiniMaxAI/MiniMax-M3 | 524.288K | $0.300 | $1.200 | — | R T S | View{
"input": 0.3,
"output": 1.2
} |
 Fireworks AI | accounts/fireworks/models/minimax-m3 | 512K | $0.300 | $1.200 | $0.060 | R T · | View{
"cache_read": 0.06,
"input": 0.3,
"output": 1.2
} |
 OpenCode Zen | minimax-m3 | 512K | $0.300 | $1.200 | $0.060 | R T · | View{
"cache_read": 0.06,
"input": 0.3,
"output": 1.2
} |
 MiniMax (minimaxi.com) | MiniMax-M3 | 1M | $0.300 | $1.200 | $0.060 | R T · | View{
"cache_read": 0.06,
"context_over_200k": {
"cache_read": 0.12,
"input": 0.6,
"output": 2.4
},
"input": 0.3,
"output": 1.2,
"tiers": [
{
"cache_read": 0.12,
"input": 0.6,
"output": 2.4,
"tier": {
"size": 512000,
"type": "context"
}
}
]
} |
 Together AI | MiniMaxAI/MiniMax-M3 | 524.288K | $0.300 | $1.200 | $0.060 | R T S | View{
"cache_read": 0.06,
"input": 0.3,
"output": 1.2
} |
 Abacus | MiniMaxAI/MiniMax-M3 | 1M | $0.300 | $1.200 | — | R T · | View{
"input": 0.3,
"output": 1.2
} |
 Deep Infra | MiniMaxAI/MiniMax-M3 | 524.288K | $0.300 | $1.200 | $0.060 | R T · | View{
"cache_read": 0.06,
"input": 0.3,
"output": 1.2
} |
 Pioneer | MiniMaxAI/MiniMax-M3 | 1M | $0.300 | $1.200 | $0.060 | R T · | View{
"cache_read": 0.06,
"cache_write": 0.3,
"input": 0.3,
"output": 1.2
} |
 CrossModel | minimax/minimax-m3 | 1.024M | $0.330 | $1.320 | $0.066 | R T · | View{
"cache_read": 0.066,
"cache_write": 0.33,
"context_over_200k": {
"cache_read": 0.132,
"cache_write": 0.66,
"input": 0.66,
"output": 2.63
},
"input": 0.33,
"output": 1.32,
"tiers": [
{
"cache_read": 0.132,
"cache_write": 0.66,
"input": 0.66,
"output": 2.63,
"tier": {
"size": 512000,
"type": "context"
}
}
]
} |
 Wafer | MiniMax-M3 | 1.04858M | $0.330 | $1.320 | $0.070 | R T S | View{
"cache_read": 0.07,
"cache_write": 0,
"context_over_200k": {
"cache_read": 0.13,
"cache_write": 0,
"input": 0.66,
"output": 2.64
},
"input": 0.33,
"output": 1.32,
"tiers": [
{
"cache_read": 0.13,
"cache_write": 0,
"input": 0.66,
"output": 2.64,
"tier": {
"size": 512000,
"type": "context"
}
}
]
} |
 Cortecs | minimax-m3 | 512K | $0.355 | $1.775 | $0.089 | R T · | View{
"cache_read": 0.089,
"input": 0.355,
"output": 1.775
} |
 ZenMux | minimax/minimax-m3 | 512K | $0.600 | $2.400 | — | R T · | View{
"input": 0.6,
"output": 2.4
} |
 Synthetic | hf:MiniMaxAI/MiniMax-M3 | 524.288K | $0.600 | $1.200 | $0.600 | R T S | View{
"cache_read": 0.6,
"input": 0.6,
"output": 1.2
} |
 LLM Gateway | minimax-m3 | 512K | $0.600 | $2.400 | $0.120 | R T · | View{
"cache_read": 0.12,
"input": 0.6,
"output": 2.4
} |
 Merge Gateway | minimax/minimax-m3 | 512K | $0.600 | $2.400 | — | R T · | View{
"input": 0.6,
"output": 2.4
} |