Official site · 🇨🇳 China
| Model | Intelligence | tok/s | $/M in | $/M out | $ / session | Cache |
|---|---|---|---|---|---|---|
| Tencent Hy3 | 25.3 | 87.7 | $0.13 | $0.53 | $0.0000 | 0.0% |
1 endpoints, cheapest first. This is the view the model-by-model tables cannot give you: what one provider actually offers, and at what precision.
| Model | Quant | $/M in | $/M out | Context | Uptime 30m |
|---|---|---|---|---|---|
| Tencent Hy3 | fp8 | $0.13 | $0.53 | 262,144 | 99.8% |
Everyone serving these models, cheapest first, with the numeric precision each one runs. The lab is often not the cheapest place to buy its own model.