Hy3 pricing across providers
Across tracked provider offerings, input runs $0.083–$0.200 per million tokens and output $0.330–$0.800 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Tencent at $0.024 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 6 of 6 offerings publish a cache-read rate; 5 of 6 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Hy3
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for Hy3
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Tencent | fp8 | $0.083 | $0.330 | $0.021 | $0.024 | 100.00% |
| Novita | unknown | $0.140 | $0.580 | $0.035 | $0.040 | 100.00% |
| GMI Cloud | bf16 | $0.140 | $0.580 | $0.035 | $0.040 | 100.00% |
| OpenCode | — | $0.140 | $0.580 | $0.035 | $0.040 | — |
| Phala | unknown | $0.150 | $0.640 | $0.040 | $0.046 | 100.00% |
| Atlascloud | fp8 | $0.200 | $0.800 | $0.050 | $0.057 | 100.00% |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.