Skip to contentx402 is live on Robinhood Chain: agents can now pay for any model, per call, in USDG →
OmniRail
← All models

OpenAI · Language model

gpt-oss-safeguard-20b

openai/gpt-oss-safeguard-20b
  • Language
Released Oct 29, 2025

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...

Specifications

Context window
131,072 tokens
Max output
65,536 tokens
Input
text
Output
text
Reasoning
always on
Tokenizer
GPT

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

  • max_tokens
  • reasoning
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-oss-safeguard-20b","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'