OpenAI: gpt-oss-safeguard-20b

moderation20B

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b.

Context
131K
Max output
66K
Input price
$0.08/1M tokens
Output price
$0.3/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode

Details

Model IDopenai/gpt-oss-safeguard-20b
Provider OpenRouter
Creator OpenAI
Familygpt-oss
License—
Status—
Typemoderation
Input modalitiestext
Output modalitiestext
Open weight—
Parameters20B
Architecture—
Context window131K tokens
Max input—
Max output66K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.08
Output
$0.3
Cache write
—
Cache read
$0.04
Batch in
—
Batch out
—

Family Comparison: gpt-oss

ModelContextMax outPricing
OpenAI: gpt-oss-120b (free)131K131K—
OpenAI: gpt-oss-20b (free)131K33K—
OpenAI: gpt-oss-20b131K33K$0.02$0.09
OpenAI: gpt-oss-20b (batch)131K118K$0.02$0.11
OpenAI: gpt-oss-120b (batch)131K118K$0.03$0.14
OpenAI: gpt-oss-safeguard-20b131K66K$0.08$0.3
OpenAI: gpt-oss-120b131K66K$0.15$0.6

API

GET/v1/models/openrouter/openai/gpt-oss-safeguard-20b