reroute

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...

Modalities
In / Out Price
$0.075 / $0.30 per 1M
Context
131K
Released
Oct 29, 2025
Knowledge Cutoff
—

API

Reroute speaks the OpenAI Chat Completions format. Point any OpenAI SDK at https://www.reroute.wtf/api/v1 and use openai/gpt-oss-safeguard-20b as the model.

You need an API key
Keys start with sk-rr-v1- and are shown once.
Create API key
curl https://www.reroute.wtf/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $REROUTE_API_KEY" \
  -d '{
  "model": "openai/gpt-oss-safeguard-20b",
  "messages": [
    { "role": "user", "content": "What is the meaning of life?" }
  ]
}'

Streaming

Set stream: true to receive server-sent events. The final chunk carries usage and cost.

curl -N https://www.reroute.wtf/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $REROUTE_API_KEY" \
  -d '{ "model": "openai/gpt-oss-safeguard-20b", "stream": true,
        "messages": [{ "role": "user", "content": "Count to five" }] }'