Model overview
- Model ID: tencent/hy4-preview
- Provider: tencent
- Type: language
- Context window: 1,024,000 tokens
- Max output tokens: 64,000
Tags: reasoning, tool-use, implicit-caching
Model pricing
| Metric | Value |
|---|---|
Input tokens (/1M) | $0.83 |
Output tokens (/1M) | $2.50 |
Image generation | n/a |
Cached input read (/1M) | $0.04 |
Cached input write (/1M) | n/a |
Pricing source | gateway |