MiMo-V2.6-Flash

MiMo-V2.6-Flash is a multimodal model from Xiaomi for coding agents and long-context automation. It is part of the MiMo line, succeeding MiMo-V2.5-Pro. It has a context window of 1,048,576 tokens and a maximum output of 131,072 tokens. It accepts audio, image, text, and video, and returns text. It supports reasoning mode and tool calling. Weights are open. Pricing starts at $0.04 per million input tokens and $0.28 per million output tokens, with cached input at $0.0027 per million tokens.

Against MiMo-V2.5-Pro: input $0.40 to $0.04, output $0.80 to $0.28, cached input $0.003 to $0.0027.

Range across the hosts that serve it: up to $0.1692 per 1M input tokens.

• ·1M token context window for long documents
• ·Accepts audio, image, text, and video inputs
• ·Supports reasoning mode and tool calling
• ·Open weights for customization
• ·131k token max output

• Reach for it for coding agents that need long context
• Reach for it for multimodal automation pipelines
• Reach for it for processing long videos or documents
• Reach for it for tool-calling workflows

19 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 image and video input?

Yes, it accepts audio, image, text, and video inputs, and returns text output.

Are the weights open?

Yes, the weights are open. It also supports reasoning mode and tool calling.