Qwen3.6 35B A3B pricing across providers
Across tracked provider offerings, input runs $0.045–$0.250 per million tokens and output $0.300–$1.80 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Engy at $0.017 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 10 of 11 offerings publish a cache-read rate; 7 of 11 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Qwen3.6 35B A3B
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 Qwen3.6 35B A3B
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) |
|---|---|---|---|---|---|---|
| Engy | — | $0.045 | $0.300 | $0.015 | $0.017 | — |
| Darkbloom | fp4 | $0.050 | $0.700 | $0.025 | $0.029 | 96.00% |
| Parasail | fp8 | $0.100 | $0.900 | $0.025 | $0.031 | 100.00% |
| Akashml | fp8 | $0.100 | $0.900 | $0.050 | $0.055 | 100.00% |
| Coreweave | fp8 | $0.100 | $0.950 | $0.050 | $0.056 | 100.00% |
| Dekallm | unknown | $0.100 | $1.00 | $0.050 | $0.056 | 100.00% |
| Phala | unknown | $0.200 | $1.27 | $0.056 | $0.066 | 100.00% |
| DeepInfra | — | $0.100 | $0.950 | $0.100 | $0.104 | — |
| Venice | fp8 | $0.100 | $1.00 | — | $0.104 | 95.65% |
| SiliconFlow | fp8 | $0.240 | $1.80 | $0.150 | $0.160 | — |
| Atlascloud | fp8 | $0.250 | $1.25 | $0.250 | $0.255 | — |
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.