OpenAI

gpt-oss-safeguard-20b

by OpenAItext->text1 endpoint

Overview

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...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
131.1K tokens
Max Output
65.5K tokens
Tokenizer
GPT
Uptime (24h)
10000.0%

Supported Parameters

include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Pricing

Per 1M tokens
Input$0.07
Output$0.30
Cache read$0.04
Added
October 29, 2025
Last synced 9/20/2026