MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 1.02T total and 42B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning and groupwise agentic grading, it is built for demanding agentic work including long-horizon coding, multi-tool agents and cybersecurity tasks.
This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.
Modalities
In / out price
$0.43 / $0.87per 1M
Cached price
$0.0036per 1M
Context
1M
Max output
16K
Providers
1 routeCompare providers by price, privacy, and speed.
| Private | $0.43 | $0.87 | $0.0036 | 1M | 16K | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
7Uptime
FAQ
Common questions about MiMo V2.6 Pro.