gpt-oss-120b pricing across providers
Across tracked provider offerings, input runs $0.030–$0.350 per million tokens and output $0.100–$0.750 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 $0.015 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 18 of 29 offerings publish a cache-read rate; 21 of 29 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to gpt-oss-120b
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 gpt-oss-120b
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 | $0.060 | $0.420 | $0.012 | $0.015 | 100.00% |
| Near Ai | fp4 | $0.030 | $0.150 | $0.015 | $0.016 | 100.00% |
| Synthetic | — | $0.100 | $0.100 | $0.020 | $0.022 | — |
| Bytedance | — | $0.100 | $0.500 | $0.020 | $0.024 | — |
| Venice | int4 | $0.030 | $0.150 | $0.030 | $0.031 | 100.00% |
| Coreweave | fp4 | $0.030 | $0.170 | $0.030 | $0.031 | 100.00% |
| Dekallm | bf16 | $0.030 | $0.180 | $0.030 | $0.031 | 100.00% |
| Akashml | bf16 | $0.030 | $0.187 | $0.030 | $0.031 | 100.00% |
| Runware | — | $0.032 | $0.140 | $0.032 | $0.033 | — |
| Sail Research | fp4 | $0.060 | $0.400 | $0.030 | $0.033 | 100.00% |
| DeepInfra | — | $0.037 | $0.170 | — | $0.038 | — |
| Crusoe | bf16 | $0.050 | $0.250 | $0.050 | $0.051 | 100.00% |
| Mancer 2 | fp8 | $0.050 | $0.250 | — | $0.051 | 100.00% |
| Novita | fp4 | $0.050 | $0.250 | — | $0.051 | 100.00% |
| Parasail | fp4 | $0.100 | $0.750 | $0.055 | $0.060 | 100.00% |
| SiliconFlow | fp8 | $0.150 | $0.600 | $0.075 | $0.080 | 100.00% |
| Groq | unknown | $0.150 | $0.600 | $0.075 | $0.080 | 100.00% |
| unknown | $0.090 | $0.360 | — | $0.091 | 0.00% | |
| Hyper | — | $0.178 | $0.680 | $0.089 | $0.094 | — |
| Baseten | fp4 | $0.100 | $0.500 | $0.100 | $0.102 | 100.00% |
| Nebius | fp4 | $0.150 | $0.600 | $0.100 | $0.104 | 100.00% |
| Aster Labs | — | $0.150 | $0.600 | — | $0.152 | — |
| Amazon | unknown | $0.150 | $0.600 | — | $0.152 | 100.00% |
| Phala | unknown | $0.150 | $0.600 | — | $0.152 | 100.00% |
| Together | unknown | $0.150 | $0.600 | — | $0.152 | 100.00% |
| Mara | unknown | $0.150 | $0.750 | — | $0.153 | 90.91% |
| Scx Ai | — | $0.170 | $0.550 | — | $0.172 | — |
| SambaNova | — | $0.220 | $0.590 | — | $0.222 | — |
| Cerebras | fp16 | $0.350 | $0.750 | $0.350 | $0.352 | 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.