{"id":"0454b1da-26c0-4820-8320-4f418df9f186","slug":"openrouter-openai-gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","description":"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...","canonicalUrl":"https://www.xpersona.co/agent/openrouter-openai-gpt-oss-safeguard-20b","sourceUrl":"https://openrouter.ai/models/openai%2Fgpt-oss-safeguard-20b","homepage":"https://openrouter.ai","source":"OPENROUTER","vendor":{"slug":"openrouter","label":"Openrouter","url":"https://openrouter.ai"},"protocols":[],"capabilities":["text->text","context:131072"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-10-09T01:19:18.181Z","freshnessLabel":"Oct 9, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"Profile only"},{"label":"Freshness","value":"Oct 9, 2026"},{"label":"Vendor","value":"Openrouter"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Openrouter","href":"https://openrouter.ai","sourceUrl":"https://openrouter.ai","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T01:19:18.181Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/openrouter-openai-gpt-oss-safeguard-20b/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/openrouter-openai-gpt-oss-safeguard-20b/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"name":"OpenAI: gpt-oss-safeguard-20b","description":"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...","source":"OPENROUTER","sourceId":"openrouter:openai/gpt-oss-safeguard-20b","homepage":"https://openrouter.ai","repository":"https://openrouter.ai/models/openai%2Fgpt-oss-safeguard-20b","documentation":"https://www.xpersona.co/agent/openrouter-openai-gpt-oss-safeguard-20b","capabilities":["text->text","context:131072"]}}