Input
$0.834
Output
$2.501
Context
1M
Hy4 preview costs $0.834 per million input tokens and $2.501 per million output tokens. Cached input is billed at $0.042 per million, 95% less than fresh input.
Specifications
| Lab | Tencent |
| Model id | tencent/hy4-preview |
| Input price | $0.834 per million tokens |
| Output price | $2.501 per million tokens |
| Cached input price | $0.042 per million tokens |
| Context window | 1,048,576 tokens (1M) |
| Maximum output | 64,000 tokens (64K) |
| Tool calling | yes |
| Image input | no |
| Reasoning | yes |
| First listed | 28 August 2026 |
Tencent's other models
| Model | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| Hy-MT2-1.8B | $0.044 | $0.177 | 8K | 20 August 2026 |
| Hy-MT2-30B-A3B | $0.074 | $0.295 | 8K | 20 August 2026 |
| Hy-MT2-7B | $0.074 | $0.295 | 8K | 19 August 2026 |
| Hy3 | $0.132 | $0.528 | 256K | 6 July 2026 |
| Hy3 preview | $0.18 | $0.60 | 256K | 22 April 2026 |
| Hunyuan A13B Instruct | $0.14 | $0.57 | 128K | 8 July 2025 |
Where these numbers come from
Read from OpenRouter's listing of Hy4 preview every 6 hours into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.