MiMo-V2.6-Pro

MiMo-V2.6-Pro is Xiaomi's Pro model in the MiMo line, built for multimodal coding agents and long-context automation. It accepts audio, image, text, and video inputs and returns text. It has a context window of 1,048,576 tokens and a maximum output of 131,072 tokens. The weights are open. It supports reasoning mode and tool calling. Pricing starts at $0.43 per million input tokens and $0.87 per million output tokens, with cached input at $0.0036 per million tokens. It is served by 19 hosts.

Against MiMo-V2.5-Pro: input $0.40 to $0.43, output $0.80 to $0.87, cached input $0.003 to $0.0036.

Range across the hosts that serve it: up to $0.5077 per 1M input tokens.

• ·1M token context window
• ·131K token max output
• ·Accepts audio, image, text, video
• ·Supports reasoning and tool calling
• ·Open weights available

• Reach for it for long-context automation
• Reach for it for multimodal coding agents
• Reach for it for processing large inputs with video and audio
• Reach for it for building agents with tool calling

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

• 8[AINews] Opus 5.5 is good at explainer videos2026-09-29
• 8[AINews] The Future of Latent Space2026-09-26

2 signals of the archive mention this model, each scored against the published bar. This list is rebuilt from the archive at every build, so it cannot go stale.

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.

Does it support tool calling?

Yes, it supports tool calling and reasoning mode.

What is the price?

From $0.43 per million input tokens and $0.87 per million output tokens, with cached input at $0.0036 per million tokens.