openai/gpt-oss-safeguard-20b
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 | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Groq | $0.075 | $0.300 | 131K | 100% |
gpt-oss-safeguard-20b costs $0.075 per million input tokens and $0.300 per million output tokens via OpenRouter, making it 35th cheapest of 298 paid models.
gpt-oss-safeguard-20b generates around 570 tokens per second with 229ms time-to-first-token (p50), the 2nd fastest tracked model.
gpt-oss-safeguard-20b supports a 131K-token context window and can output up to 66K tokens. It accepts text input.