Hy4 Preview is a 770B-parameter Mixture-of-Experts model from the Tencent Hy Team, with 49B parameters active per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention with IndexCache and is post-trained for software engineering, office and data analysis, game development and scientific research, with adjustable reasoning effort.
This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.
Modalities
In / out price
$0.834 / $2.501per 1M
Cached price
$0.042per 1M
Context
1M
Max output
16K
Providers
1 routeCompare providers by price, privacy, and speed.
| Private | $0.834 | $2.501 | $0.042 | 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
4Uptime
FAQ
Common questions about Hy4 Preview.