Hy4 Uncensored is the Tencent Hy Team's Hy4 with refusal behavior removed. The base model is a 770B-parameter Mixture-of-Experts model with 49B parameters active per token and a 1M-token context window, using Gated DeepSeek Sparse Attention, and is post-trained for software engineering, office and data analysis work and scientific research, with adjustable reasoning effort. This variant takes text input and produces text output.
Modalities
In / out price
$1.85 / $3.70per 1M
Cached price
$0.35per 1M
Context
1M
Max output
66K
Providers
1 routeCompare providers by price, privacy, and speed.
Silk Compute | Private | $1.85 | $3.70 | $0.35 | 1M | 66K | — | — |
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
4Uptime
FAQ
Common questions about Hy4 Uncensored.