Qwen3.5 397B A17B pricing across providers
Across tracked provider offerings, input runs $0.390–$0.750 per million tokens and output $2.34–$4.50 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is DigitalOcean at $0.138 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 6 of 10 offerings publish a cache-read rate; 4 of 10 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Qwen3.5 397B A17B
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 Qwen3.5 397B A17B
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) |
|---|---|---|---|---|---|---|
| Digitalocean | unknown | $0.550 | $3.50 | $0.110 | $0.138 | — |
| Streamlake | unknown | $0.600 | $3.60 | $0.120 | $0.149 | — |
| DeepInfra | — | $0.450 | $3.00 | $0.220 | $0.240 | — |
| Phala | unknown | $0.550 | $3.50 | $0.225 | $0.249 | 100.00% |
| Parasail | fp8 | $0.500 | $3.60 | $0.300 | $0.322 | 100.00% |
| Alibaba | unknown | $0.390 | $2.34 | — | $0.400 | — |
| Atlascloud | fp8 | $0.550 | $3.50 | $0.550 | $0.565 | — |
| GMI Cloud | fp8 | $0.600 | $3.60 | — | $0.615 | — |
| Novita | unknown | $0.600 | $3.60 | — | $0.615 | 100.00% |
| Venice | unknown | $0.750 | $4.50 | — | $0.769 | 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.