openai

OpenAI: gpt-oss-safeguard-20b

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...

text

Try in Playground ↗

Input / 1M tokens$0.075

Output / 1M tokens$0.3

Context window131,072

Maximum output65,536

Provider-supported parameters

These are upstream capabilities. Jevrouter supports the subset described in the API contract; chat input is currently text only.

include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_pstreamdeveloper_role

Capabilities are imported from OpenRouter’s catalog. This does not mean every model has been independently tested by Jevrouter.

Catalog updated: 2026-09-22T10:51:50.887Z · Price version: cmub11b8p00ztr82g3zj2fxpt:1

Provider pricing fields · USD per indicated unit

{
  "prompt": "0.000000075",
  "completion": "0.0000003",
  "input_cache_read": "0.0000000375"
}

Make a request

curl --no-buffer https://api.jevrouter.io/v1/chat/completions \
  -H "Authorization: Bearer $JEVROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<'JSON'
{
  "model": "openai/gpt-oss-safeguard-20b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 1024
}
JSON

Plan your integration

Connect with the OpenAI Python SDK →Estimate this model’s cost →Budgets, request status and safe retries →

Source: OpenRouter model catalog. Imported descriptions and capabilities are provider declarations, not independent benchmark results. Jevrouter currently uses OpenRouter as its managed upstream.