MiMo-V2.5

MiMo-V2.5 is an open model from Xiaomi for multimodal coding agents and long-context automation. It is the latest in the MiMo line, following MiMo-V2-Pro. It has a context window of 1,048,576 tokens and a maximum output of 131,072 tokens. Weights are open. It supports reasoning mode and tool calling. It accepts audio, image, text, and video, and returns text. Pricing starts at $0.14 per million input tokens and $0.28 per million output tokens, with cached input at $0.0028 per million tokens.

Against MiMo-V2-Pro: input $0.435 to $0.14, output $0.87 to $0.28, cached input $0.0036 to $0.0028.

Range across the hosts that serve it: up to $0.40 per 1M input tokens.

• ·1M token context window
• ·131K token output limit
• ·Accepts audio, image, text, video
• ·Open weights with reasoning mode
• ·Tool calling support

• Reach for it for coding agents that handle long contexts
• Reach for it for multimodal automation tasks
• Reach for it for workflows needing tool calling
• Reach for it for large-scale document processing

22 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window size?

The context window is 1,048,576 tokens, and the maximum output is 131,072 tokens.

Does it support tool calling and reasoning?

Yes, it supports both reasoning mode and tool calling.

What is the pricing?

Input starts at $0.14 per million tokens, output at $0.28 per million, and cached input at $0.0028 per million.