gpt-oss-20b API pricing
Of the 6 providers checked, CoreWeave lists the lowest blended rate for gpt-oss-20b: $0.03 input and $0.13 output per 1M tokens, on its pricing page as of 27 September 2026.
The smaller of OpenAI's two open-weight models, meant for lower latency and for running locally. It has the same Apache 2.0 license as gpt-oss-120b.
- Creator
- OpenAI
- Released
- 5 August 2025
- Weights
- Open
- License
- Apache 2.0
- Size
- 21B total, 4B active
- Context
- 128K tokens
- Input
- text
- Model card
- Hugging Face
Facts from the model card, checked 25 Sep 2026.
Across 6 providers, the most expensive charges 4.1ร the cheapest on a blended basis.
Prices by provider
Per 1M tokens, on-demand, sorted cheapest first by blended cost (3:1 input to output). Off-peak and long-context rates are listed on each provider's page.
| # | Provider | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|---|
| 1 | CoreWeave | $0.03 | โ | $0.13 | 27 Sep 2026 | |
| 2 | DeepInfra | $0.03 | โ | $0.14 | 25 Sep 2026 | |
| 3 | Novita AI | $0.04 | โ | $0.15 | 25 Sep 2026 | |
| 4 | SiliconFlow | $0.04 | โ | $0.18 | 25 Sep 2026 | |
| 5 | Groq | $0.075 | โ | $0.30 | 25 Sep 2026 | |
| 6 | Cloudflare Workers AI | $0.20 | โ | $0.30 | 27 Sep 2026 | @cf/openai/gpt-oss-20b |
Each price was read off the provider's own pricing page on the date shown; the date links to that page. Providers that publish no per-token price for this model are not listed. The same data is open under CC-BY at /api/query/prices.
Compare every inference provider on free tiers, hosting and EU availability in the inference APIs table.
Is your product missing?