← model directory

openai

OpenAI: gpt-oss-safeguard-20b

openai/gpt-oss-safeguard-20b

↓ runs free on your own hardware

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...

specs & pricing
Type
text
Provider
openai
Model ID
openai/gpt-oss-safeguard-20b
Capabilities
tools, reasoning
Context window
131K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.083 / 1M tokens
Output price
$0.33 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

OpenAI: gpt-oss-safeguard-20b — pricing, context & specs | Wide Area Intelligence