| Spec | gpt-oss-120b | gpt-oss-20b |
|---|---|---|
| Lowest input | $0.037DeepInfra | $0.03DeepInfra |
| Lowest output | $0.17DeepInfra | $0.14DeepInfra |
| Lowest cached input | Not listed | Not listed |
| Context | 131K | 131K |
| Max output | 131K | 131K |
| Providers | 2 | 1 |
| Released | August 5, 2025 | August 5, 2025 |
| Weights | Open | Open |
| Lab | OpenAI | OpenAI |
| Model ID | openai/gpt-oss-120b | openai/gpt-oss-20b |
USD per 1M tokens, as of November 5, 2026.
| Provider | gpt-oss-120b | gpt-oss-20b |
|---|---|---|
| DeepInfra | $0.037 / $0.17 | $0.03 / $0.14 |
| Phala | $0.15 / $0.60 | – |
Input / output, USD per 1M tokens.
| Model | 1,000 chat replies2K in, 500 out each | 1,000 agent tasks50K in, 5K out each | Monthly batch job500M in, 50M out |
|---|---|---|---|
| gpt-oss-120bDeepInfra | $0.16 | $2.70 | $27.00 |
| gpt-oss-20bDeepInfra | $0.13 | $2.20 | $22.00 |
On each model's cheapest provider by input plus output list price.
Input: gpt-oss-20b at $0.03 per million input tokens vs $0.037 (gpt-oss-120b), 23% lower. Output: gpt-oss-20b at $0.14 per million output tokens vs $0.17 (gpt-oss-120b), 21% lower. Lowest listed prices as of November 5, 2026.
Both list 131K tokens of context.
1 provider serves both: DeepInfra. gpt-oss-120b has 2 providers in total and gpt-oss-20b has 1.
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "openai/gpt-oss-120b" to "openai/gpt-oss-20b".
