Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | tencentHy4-previewRemove × |
|---|---|
| What’s different | Hy4 preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy Team, with 49B parameters activated per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention… |
| Date | Aug 27, 2026Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.834 in / $2.501 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗ |
| Provider endpoints | 8 endpoints → |
Specifications | |
| Context window | 1M |
| Max output | 64K |
| Parameters | — |
| Tool calling | Supported |
| Structured output | Supported |
| Reasoning | Supported |
| Prompt caching | Supported |
| Open weights | Supported |