Input
$0.035
Output
$0.1405
Context
1M
Hy4 flash costs $0.035 per million input tokens and $0.1405 per million output tokens. Cached input is billed at $0.0015 per million, 96% less than fresh input.
Specifications
| Lab | Tencent |
| Model id | tencent/hy4-flash |
| Input price | $0.035 per million tokens |
| Output price | $0.1405 per million tokens |
| Cached input price | $0.0015 per million tokens |
| Context window | 1,048,576 tokens (1M) |
| Maximum output | 65,536 tokens (64K) |
| Tool calling | yes |
| Image input | yes |
| Reasoning | yes |
| First listed | 16 November 2026 |
Tencent's other models
| Model | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| Hy4 | $0.417 | $1.2505 | 1M | 4 November 2026 |
| Hy4 preview | $0.834 | $2.501 | 1M | 28 August 2026 |
| 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 |
Where these numbers come from
Read from OpenRouter's listing of Hy4 flash 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.