All Models
MiniMax-M3
MiniMax multimodal model for long-context coding, perception, and agent planning
Benchmarks
Available Providers (38)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Nvidia | minimaxai/minimax-m3 | $0/MTok | $0/MTok | 1M | 16.4K | |
 Kenari | minimax-m3 | $0/MTok | $0/MTok | 512K | 128K | |
 MiniMax Token Plan (minimaxi.com) | MiniMax-M3 | $0/MTok | $0/MTok | 1M | 128K | |
 MiniMax Token Plan (minimax.io) | MiniMax-M3 | $0/MTok | $0/MTok | 1M | 128K | |
 SCNet Token Plan | MiniMax-M3 | $0/MTok | $0/MTok | 512K | 128K | |
 EmpirioLabs AI | minimax-m3 | $0.23/MTok | $0.90/MTok | 1M | 524.3K | |
 Weights & Biases | MiniMaxAI/MiniMax-M3 | $0.23/MTok | $0.96/MTok | 262.1K | 262.1K | |
 Requesty | minimax-m3 | $0.24/MTok | $0.96/MTok | 1M | 128K | |
 Deep Infra | MiniMaxAI/MiniMax-M3 | $0.28/MTok | $1.10/MTok | 524.3K | 128K | |
 Lilac | minimaxai/minimax-m3 | $0.28/MTok | $1.10/MTok | 1.0M | 1.0M | |
 NanoGPT | minimax/minimax-m3 | $0.30/MTok | $1.20/MTok | 512K | 80K | |
 Jalapeno Cloud | MiniMax-M3 | $0.30/MTok | $1.20/MTok | 524.3K | 128K | |
 Hugging Face | MiniMaxAI/MiniMax-M3 | $0.30/MTok | $1.20/MTok | 524.3K | 128K | |
 OpenRouter | minimax/minimax-m3 | $0.30/MTok | $1.20/MTok | 1.0M | 512K | |
 OpenCode Go | minimax-m3 | $0.30/MTok | $1.20/MTok | 1M | 131.1K | |
 Nebius Token Factory | MiniMaxAI/MiniMax-M3 | $0.30/MTok | $1.20/MTok | 1.0M | 1.0M | |
 Merge Gateway | minimax/minimax-m3 | $0.30/MTok | $1.20/MTok | 1M | 128K | |
 Together AI | MiniMaxAI/MiniMax-M3 | $0.30/MTok | $1.20/MTok | 524.3K | 250K | |
 OpenCode Zen | minimax-m3 | $0.30/MTok | $1.20/MTok | 512K | 128K | |
 MiniMax (minimaxi.com) | MiniMax-M3 | $0.30/MTok | $1.20/MTok | 1M | 128K | |
 ClinePass | cline-pass/minimax-m3 | $0.30/MTok | $1.20/MTok | 512K | 128K | |
 Vercel AI Gateway | minimax/minimax-m3 | $0.30/MTok | $1.20/MTok | 1M | 1M | |
 Eden AI | minimax/MiniMax-M3 | $0.30/MTok | $1.20/MTok | 524.3K | 128K | |
 DevPass (LLM Gateway) | minimax-m3 | $0.30/MTok | $1.20/MTok | 1.0M | 128K | |
 Kilo Gateway | minimax/minimax-m3 | $0.30/MTok | $1.20/MTok | 524.3K | 512K | |
 Pioneer | MiniMaxAI/MiniMax-M3 | $0.30/MTok | $1.20/MTok | 1M | 131.1K | |
 Fireworks AI | accounts/fireworks/models/minimax-m3 | $0.30/MTok | $1.20/MTok | 512K | 512K | |
 Abacus | MiniMaxAI/MiniMax-M3 | $0.30/MTok | $1.20/MTok | 1M | 131.1K | |
 MiniMax (minimax.io) | MiniMax-M3 | $0.30/MTok | $1.20/MTok | 1M | 128K | |
 Charm Hyper | minimax-m3 | $0.33/MTok | $1.31/MTok | 512K | 512K | |
 CrossModel | minimax/minimax-m3 | $0.33/MTok | $1.32/MTok | 1.0M | 512K | |
 Wafer | MiniMax-M3 | $0.33/MTok | $1.32/MTok | 1.0M | 128K | |
 Cortecs | minimax-m3 | $0.40/MTok | $1.98/MTok | 1.0M | 1.0M | |
 TensorX | minimax/minimax-m3 | $0.40/MTok | $2/MTok | 1.0M | 131.1K | |
 Synthetic | hf:MiniMaxAI/MiniMax-M3 | $0.60/MTok | $1.20/MTok | 524.3K | 65.5K | |
 ZenMux | minimax/minimax-m3 | $0.60/MTok | $2.40/MTok | 512K | 128K | |
 Ofox | minimax/minimax-m3 | $0.60/MTok | $2.40/MTok | 512K | 128K | |
 Ollama Cloud | minimax-m3 | —/MTok | —/MTok | 512K | 131.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output