# GPT OSS Safeguard 20B API pricing

No price from the maker itself is on record for GPT OSS Safeguard 20B. The lowest of 10 providers is Amazon Bedrock: $0.07 per 1M input tokens and $0.2 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 65.5K output tokens per request.

- Type: Text
- Context: 131K
- Max output: 65.5K
- Released: 2025-10-29
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | openai.gpt-oss-safeguard-20b | $0.07 | $0.2 | — | Lowest |
| [Eden AI](https://docs.edenai.co) | amazon/openai.gpt-oss-safeguard-20b | $0.07 | $0.2 | — |  |
| [Eden AI](https://docs.edenai.co) | amazon/openai.gpt-oss-safeguard-20b@us | $0.07 | $0.2 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | openai/gpt-oss-safeguard-20b | $0.07 | $0.2 | $0 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | openai/gpt-oss-safeguard-20b | $0.07 | $0.2 | — |  |
| [LowRouter](https://lowrouter.ai/docs/models/available) | auto/openai/gpt-oss-safeguard-20b | $0.08 | $0.24 | — |  |
| [Eden AI](https://docs.edenai.co) | groq/openai/gpt-oss-safeguard-20b | $0.075 | $0.3 | $0.0375 |  |
| [Groq](https://console.groq.com/docs/models) | openai/gpt-oss-safeguard-20b | $0.075 | $0.3 | $0.0375 | Beta |
| [Kilo Gateway](https://kilo.ai) | openai/gpt-oss-safeguard-20b | $0.075 | $0.3 | $0.0375 |  |
| [NanoGPT](https://docs.nano-gpt.com) | openai/gpt-oss-safeguard-20b | $0.075 | $0.3 | — |  |
| [OpenRouter](https://openrouter.ai/models) | openai/gpt-oss-safeguard-20b | $0.075 | $0.3 | $0.0375 |  |
| [AI/ML API](https://docs.aimlapi.com) | openai/gpt-oss-safeguard-20b | $0.07935 | $0.3174 | $0.039675 |  |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/openai/gpt-oss-safeguard-20b/