TokenRoute
Get started
Back to models

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...

Try in Playground

Pricing

Input$0.0525 /M
Output$0.2100 /M
Cache read$0.0262 /M

Specs

Context length131.1K tokens
Max output65.5K tokens
Inputtext
Outputtext

Quickstart

Point the OpenAI SDK at https://tokenroute.app/api/v1 and use a TokenRoute API key.

bash
curl https://tokenroute.app/api/v1/chat/completions \
  -H "Authorization: Bearer $TOKENROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-safeguard-20b",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Supported parameters

include_reasoning
max_tokens
reasoning
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_p