Tencent
Hy4 preview
tencent/hy4-preview
Input
$0.751
per 1M tokens
Output
$2.25
per 1M tokens
Cached input
$0.038
per 1M tokens
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...
- Released
- Context window
- 1M tokens
- Max output
- 64K tokens
- Input
- text
- Output
- text
- Reasoning
- Yes
Price history
- input $0.834 → $0.751 -10% · output $2.50 → $2.25 -10%
- input $0.751 → $0.834 +11% · output $2.25 → $2.50 +11%
- input $0.834 → $0.751 -10% · output $2.50 → $2.25 -10%
- input $0.751 → $0.834 +11% · output $2.25 → $2.50 +11%
- input $0.834 → $0.751 -10% · output $2.50 → $2.25 -10%
- input $0.751 → $0.834 +11% · output $2.25 → $2.50 +11%
- input $0.834 → $0.751 -10% · output $2.50 → $2.25 -10%
- input $0.751 → $0.834 +11% · output $2.25 → $2.50 +11%
- input $0.834 → $0.751 -10% · output $2.50 → $2.25 -10%
- input $0.751 → $0.834 +11% · output $2.25 → $2.50 +11%
Providers on OpenRouter
7 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| AtlasCloudfp8 | $0.834 | $2.50 | 1M | 100% | 100% |
| GMICloudbf16 | $0.834 | $2.50 | 262K | — | 100% |
| Novitafp8 | $0.834 | $2.50 | 1M | 100% | 100% |
| Tencentfp8 | $0.834 | $2.50 | 1M | 100% | 100% |
| SiliconFlowfp8 | $0.834 | $2.50 | 1M | 100% | 99.86% |
| DeepInfrafp4 | $0.834 | $2.50 | 1M | 100% | 99.71% |
| Cohere | $0.834 | $2.50 | 262K | 100% | 96.7% |