gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
| Provider | openai |
|---|---|
| Input price | $0.075 / 1M tokens |
| Output price | $0.300 / 1M tokens |
| Context window | 131k tokens |
| Max output | 66k tokens |
| Modalities | text |
| Model ID | openai/gpt-oss-safeguard-20b |
A 1,000-token prompt with a 500-token answer on OpenAI: gpt-oss-safeguard-20b costs roughly $0.00022. Use the OpenRouter cost calculator to price your own prompt across 400+ models, or the token counter to measure prompt length first.
PromNest stores your prompt library and lets you run any prompt on OpenAI: gpt-oss-safeguard-20b with your own OpenRouter key — including side-by-side comparison with other models. Browse 1,000+ ready-made prompt templates to start.