Inference provider
Tencent: every model it hosts
2 endpoints tracked. Hosts may use different quantizations, context limits, and serving defaults, so compare price together with reliability and configuration. On this host family, the same model costs up to 6× more depending on which endpoint serves it.
Verified 2026-10-21 · source: OpenRouter public API
| Model | Input /1M | Output /1M | Cache read | Context | Uptime 1d | Throughput |
|---|---|---|---|---|---|---|
| Tencent: Hy3fp8 | $0.132 | $0.528 | $0.033 | 262K | 100.0% | — |
| Tencent: Hy4 previewfp8 | $0.834 | $2.50 | $0.042 | 1049K | 100.0% | — |
Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.