• Playground
  • Models
  • Rankings
  • Support

Zero data retentionYour prompts and outputs are never stored or trained on

© 2026 BoundlessTermssupport@boundless.network
All models

MiMo-V2.6 Pro

by Xiaomi ~ A frontier open-weight agent that reads text, images, audio, and video

MiMo-V2.6-Pro is Xiaomi's flagship open-weight model: a 1.02T-parameter mixture-of-experts with 42B active per token. It is natively omnimodal, taking text, images, audio, and video in one model, and its 1,048,576-token context window fits long repositories, tool traces, and multi-session agent runs.

1M context
  • Text
  • Reasoning
  • Tool use
  • Image input
  • Vision
  • Audio input
  • Video input
Model weights
mimo-v2.6-proTry it in the playground

Pricing

Pricing
USD per 1M tokens.
WindowInputCached inputOutput
asap$0.44$0$0.87
What one request costs
Prompt94Ktokens
Cached prefix66Ktokens
Reply2Ktokens

$0.0138

per request to MiMo-V2.6 Pro

Prompt
88.8%
Cached
1.7%
Reply
9.5%

MiMo-V2.6 Pro: $0.01380888 per request

94,000 prompt tokens, 65,800 of them cached, and 1,500 reply tokens.

The same request, across other models