Skip to content

GPT-OSS Safeguard 20B

Tools
openai/gpt-oss-safeguard-20b

131K context · Oct 2025 · 5 upstreams

OpenAI's open-weight safety reasoning model built on gpt-oss-20b (Apache 2.0). A 21B-parameter MoE tuned for safety tasks: content classification, LLM input/output filtering, and trust & safety judgments with reasoning traces. Use it as a guardrail/judge hop in front of or behind chat models.

Bring your own keyAnyRouter has no platform route for GPT-OSS Safeguard 20B. Requests use your key and bill your provider account. AnyRouter adds no fee.
context
131K
input / 1M (list)
$0.07
output / 1M (list)
$0.20
routes
5
speed, 24h
—

Upstreams

5
  1. 1GroqYour key · not addedyour planTPS —TTFT ——
  2. 2OpenRouterYour key · not addedyour planTPS —TTFT ——
  3. 3Vercel AI GatewayYour key · not addedyour planTPS —TTFT ——
  4. 4Hugging FaceYour key · not addedyour planTPS —TTFT ——
  5. 5Nous ResearchYour key · not addedyour planTPS —TTFT ——
  • Up
  • No traffic
  • Down

Try it

Send a prompt

Details

Owner
OpenAI
Kind
Chat
Released
Oct 2025
Context
131K
Data policy
Provider retention
Endpoint
/api/v1/chat/completions

Quick start

curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-oss-safeguard-20b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'