Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
| 262K | $0.0825 | $0.33 | $0.0206 | — | — | 100.00% | |
| 262K | $0.14 | $0.58 | $0.035 | — | — | 100.00% | |
| 262K | $0.14 | $0.58 | $0.035 | — | — | 100.00% | |
| 262K | $0.15 | $0.64 | $0.04 | — | — | 100.00% | |
| 262K | $0.20 | $0.80 | $0.05 | — | — | 100.00% |