OpenAI · gpt-oss
GPT OSS 20B
Open GPT reasoning model for self-hosted agents and controllable deployments
$0.07 in · $0.30 out
per 1M tokens · provider rate closest to the median. No first-party OpenAI price was listed. The reference price is Amazon Bedrock's rate, the provider closest to the median.
Provider input prices run from $0.018 to $0.20 per 1M tokens. Output prices run from $0.09 to $0.50.
- Context
- 131,072
- Max output
- 32,768
- Cache read
- —
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Yes
- Vision
- No
- Open weights
- Yes
- License
- —
- Released
- Aug 5, 2025
- Updated in source
- Aug 5, 2025
- Knowledge
- —
- Providers
- 22
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Kilo Gateway | $0.018 | $0.09 | $0.009 | — | — |
| OpenRouter | $0.018 | $0.09 | $0.009 | — | — |
| Eden AI | $0.02 | $0.10 | $0.003 | — | — |
| CoreWeave | $0.03 | $0.13 | $0.03 | — | — |
| Vercel AI Gateway | $0.03 | $0.14 | — | — | — |
| Merge Gateway | $0.04 | $0.15 | $0.02 | — | — |
| Cortecs | $0.045 | $0.17 | — | — | — |
| Amazon Bedrockreference | $0.07 | $0.30 | — | — | — |
| OCI Generative AI | $0.07 | $0.30 | — | — | — |
| Pioneer | $0.07 | $0.30 | $0.035 | $0.07 | — |
| Prime Inference | $0.07 | $0.30 | — | — | — |
| Impossibl | $0.075 | $0.30 | $0.038 | — | — |
| Tempr Gateway | $0.075 | $0.30 | $0.038 | — | — |
| Hugging Face | $0.10 | $0.50 | — | — | — |
| LLM Gateway | $0.10 | $0.50 | — | — | — |
| AI/ML API | $0.10 | $0.41 | $0.052 | — | — |
| LowRouter | $0.11 | $0.47 | — | — | — |
| Opper | $0.12 | $0.49 | — | — | — |
| STACKIT | $0.18 | $0.29 | — | — | — |
| Cloudflare Workers AI | $0.20 | $0.30 | — | — | — |
| NanoGPT | $0.20 | $0.30 | — | — | — |
| QVAC | $0 | $0 | — | — | — |
Jobs this model qualifies for
- Coding agents — clears the bar
- Cheapest summarization — clears the bar