Qwen3 32B pricing across providers
Across tracked provider offerings, input runs $0.080–$0.360 per million tokens and output $0.280–$0.870 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is DeepInfra at $0.081 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 1 of 4 offerings publish a cache-read rate; 2 of 4 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to Qwen3 32B
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 32B
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) |
|---|---|---|---|---|---|---|
| DeepInfra | — | $0.080 | $0.280 | — | $0.081 | — |
| Tenstorrent | fp8 | $0.140 | $0.400 | $0.090 | $0.093 | 100.00% |
| SiliconFlow | fp8 | $0.140 | $0.570 | — | $0.142 | 100.00% |
| Scx Ai | — | $0.360 | $0.870 | — | $0.363 | — |
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.