All Models
MiniMax M2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
Benchmarks
Available Providers (35)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 MiniMax Coding Plan (minimax.io) | MiniMax-M2.5 | $0.00/MTok | $0.00/MTok | 204.8K | 131.1K | |
 MiniMax Coding Plan (minimaxi.com) | MiniMax-M2.5 | $0.00/MTok | $0.00/MTok | 204.8K | 131.1K | |
 Alibaba Coding Plan | MiniMax-M2.5 | $0.00/MTok | $0.00/MTok | 196.6K | 24.6K | |
 Nvidia | minimaxai/minimax-m2.5 | $0.00/MTok | $0.00/MTok | 204.8K | 131.1K | |
 Alibaba Coding Plan (China) | MiniMax-M2.5 | $0.00/MTok | $0.00/MTok | 196.6K | 24.6K | |
 Tencent Coding Plan (China) | minimax-m2.5 | $0.00/MTok | $0.00/MTok | 204.8K | 32.8K | |
 Deep Infra | MiniMaxAI/MiniMax-M2.5 | $0.27/MTok | $0.95/MTok | 204.8K | 131.1K | |
 AIHubMix | minimax-m2.5 | $0.29/MTok | $1.15/MTok | 204.8K | 131.1K | |
 D.Run (China) | public/minimax-m25 | $0.29/MTok | $1.16/MTok | 204.8K | 131.1K | |
 NanoGPT | minimax/minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 OpenRouter | minimax/minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 Fireworks AI | accounts/fireworks/models/minimax-m2p5 | $0.30/MTok | $1.20/MTok | 196.6K | 196.6K | |
 OpenCode Go | minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 Alibaba (China) | MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 Hugging Face | MiniMaxAI/MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 ZenMux | minimax/minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 NovitaAI | minimax/minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 Weights & Biases | MiniMaxAI/MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 196.6K | 196.6K | |
 OpenCode Zen | minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 Amazon Bedrock | minimax.minimax-m2.5 | $0.30/MTok | $1.20/MTok | 196.6K | 98.3K | |
 Baseten | MiniMaxAI/MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 204K | 204K | |
 Firmware | minimax-m2-5 | $0.30/MTok | $1.20/MTok | 192K | 8.2K | |
 CloudFerro Sherlock | MiniMaxAI/MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 196K | 196K | |
 Meganova | MiniMaxAI/MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 Vultr | MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 194K | 4.1K | |
 Friendli | MiniMaxAI/MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 196.6K | 196.6K | |
 Vercel AI Gateway | minimax/minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131K | |
 MiniMax (minimax.io) | MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 LLM Gateway | minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 Together AI | MiniMaxAI/MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 MiniMax (minimaxi.com) | MiniMax-M2.5 | $0.30/MTok | $1.20/MTok | 204.8K | 131.1K | |
 Cortecs | minimax-m2.5 | $0.32/MTok | $1.18/MTok | 196.6K | 196.6K | |
 Venice AI | minimax-m25 | $0.34/MTok | $1.19/MTok | 198K | 32.8K | |
 Synthetic | hf:MiniMaxAI/MiniMax-M2.5 | $0.60/MTok | $3.00/MTok | 191.5K | 65.5K | |
 Ollama Cloud | minimax-m2.5 | —/MTok | —/MTok | 204.8K | 131.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output