MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi's Pro tier in the MiMo line, built for multimodal reasoning and coding-agent execution. It is a stronger version of the previous MiMo-V2.5, released on the same day. The model has a context window of 1,048,576 tokens and a maximum output of 131,072 tokens. Its weights are open. It supports reasoning mode and tool calling, and accepts and returns text only. Pricing starts at $0.40 per million input tokens and $0.80 per million output tokens, with cached input at $0.003 per million tokens.

Against MiMo-V2-Pro: input $0.435 to $0.40, output $0.87 to $0.80, cached input $0.0036 to $0.003.

Range across the hosts that serve it: up to $1.74 per 1M input tokens.

• ·1,048,576-token context window
• ·131,072-token maximum output
• ·Reasoning mode and tool calling
• ·Open weights for self-hosting

• Reach for it for coding-agent execution
• Reach for it for long-context reasoning tasks
• Reach for it for tool-calling workflows

23 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?

1,048,576 tokens.

Is the model open source?

Yes, the weights are open.

What is the price?

From $0.40 per million input tokens and $0.80 per million output tokens, with cached input at $0.003 per million.