Tencent
Hy4 preview
Released 2026-08-28
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
You send / 1M
$0.834
tokens in
It replies / 1M
$2.50
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0023
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Io Net · fp8 | $0.834 | $2.50 | 99% | Read |
| Cohere | $0.834 | $2.50 | 100% | Read |
| DeepInfra · fp4 | $0.834 | $2.50 | 100% | Read |
| Novita · fp8 | $0.834 | $2.50 | 100% | Read |
| SiliconFlow · fp8 | $0.834 | $2.50 | 100% | Read |
| Tencent · fp8 | $0.834 | $2.50 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 64K tokens
- Repeated text is billed at $0.042 per 1M (prompt caching)
Similar models
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Zero Data Retention Long-Context AI ModelsTop No-Training Reasoning AI ModelsTop No-Training Reasoning Tool-Calling AI ModelsTop No-Training Reasoning Long-Context AI Models