MiMo-V2-Omni

MiMo-V2-Omni is a legacy model from Xiaomi's mimo line, retained for compatibility with older integrations. It is the first version of its line in the registry, released on 2026-03-18. The model has a context window of 262144 tokens and a maximum output of 131072 tokens. 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. Weights are not open. It supports reasoning mode and tool calling, accepts audio, image, pdf, text, and video, and returns text. Knowledge cutoff is 2024-12. It is served by 2 hosts.

First version of its line in the registry.

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

• ·262k token context window
• ·131k token max output
• ·Accepts audio, image, pdf, text, video
• ·Supports reasoning and tool calling
• ·Cached input at $0.0028 per million

• Reach for it for maintaining existing integrations
• Reach for it for processing mixed media inputs
• Reach for it for long-context reasoning tasks
• Reach for it for tool-assisted workflows

2 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?

The context window is 262144 tokens, and the maximum output is 131072 tokens.

What input types does it accept?

It accepts audio, image, pdf, text, and video, and returns text.

Is it open weights?

No, the weights are not open. It is a proprietary model.