Back to models
gpt-oss-20b vs gpt-oss-120b
gpt-oss-20b and gpt-oss-120b: current price, context, max output, and supported operations.
Pricing comparison
| gpt-oss-20b | gpt-oss-120b | |
|---|---|---|
| Model maker | OpenAI | OpenAI |
| Delivery availability | Available | Available |
| Context window | 128K | 128K |
| Max output | 32K | 64K |
| Official price | Input$0.075per 1M tokensOutput$0.30per 1M tokens | Input$0.15per 1M tokensOutput$0.60per 1M tokens |
| Verified price | — | — |
| Model performance | Collecting data | Collecting data |
| Capabilities | JSON modeTool use | JSON modePrompt CacheReasoningTool use |
Summary
- gpt-oss-20b: —; gpt-oss-120b: —. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
- gpt-oss-120b supports 2.0x more output tokens
FAQ
Which is cheaper, gpt-oss-20b or gpt-oss-120b?
gpt-oss-20b: —; gpt-oss-120b: —. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the key differences between gpt-oss-20b and gpt-oss-120b?
gpt-oss-120b: Prompt Cache, Reasoning