Hunyuan Hy4 (preview)
Tencent's next open model, in preview
Price
What the gateway charges per million tokens: what you send in, and what the model writes back.
Source: Vercel AI Gateway, checked 2026-09-26.
- Input
- $0.834per 1M tokens
- Output
- $2.501per 1M tokensOutput costs 3x the input.
Specs
How much it reads at once, how much it writes back, and how recent its knowledge is.
Source: Vercel AI Gateway, checked 2026-09-26.
- Context window
- 1.02M tokens1,024,000
- Max output
- 64K tokens64,000
- Knowledge cutoff
- Not listed
- Released
- Type
- Language
- Modalities
- Takes text. Returns text.
- Gateway ID
tencent/hy4-preview
Capabilities
What the gateway says this model supports.
Source: Vercel AI Gateway, checked 2026-09-26.
- Reasoning
- Tool use
- Implicit caching
Data handling
What happens to your prompts, and what you have to switch on.
Source: Vercel AI Gateway, checked 2026-09-26.
ZDRNo provider
Zero data retention
Not offered by any provider on the Vercel AI Gateway.
NTNo provider
No training on prompts
Not offered by any provider on the Vercel AI Gateway.
Also by Tencent
Friday
The brief, by email
Five to seven links an issue, each with what to do about it.
Unsubscribe from any issue.