Hy4 preview pricing across providers
Across tracked provider offerings, input runs $0.751–$0.834 per million tokens and output $2.25–$2.50 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 $0.067 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 8 of 8 offerings publish a cache-read rate; 5 of 8 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Hy4 preview
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 Hy4 preview
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 | $0.751 | $2.25 | $0.038 | $0.067 | 100.00% |
| DeepInfra | — | $0.834 | $2.50 | $0.042 | $0.074 | — |
| GMI Cloud | bf16 | $0.834 | $2.50 | $0.042 | $0.074 | — |
| Atlascloud | fp8 | $0.834 | $2.50 | $0.042 | $0.074 | 100.00% |
| Cohere | unknown | $0.834 | $2.50 | $0.042 | $0.074 | 100.00% |
| Novita | fp8 | $0.834 | $2.50 | $0.042 | $0.074 | 100.00% |
| SiliconFlow | fp8 | $0.834 | $2.50 | $0.042 | $0.074 | 100.00% |
| OpenCode | — | $0.834 | $2.50 | $0.042 | $0.074 | — |
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.