gpt-oss-safeguard-20b

OpenAI's first open weight reasoning model specifically trained for safety classification tasks. Fine-tuned from GPT-OSS, this model helps classify text content based on customizable policies, enabling bring-your-own-policy Trust & Safety AI where your own taxonomy, definitions, and thresholds guide classification decisions.

Model overview

Model ID: openai/gpt-oss-safeguard-20b
Provider: openai
Type: language
Context window: 131,072 tokens
Max output tokens: 65,536

Tags: reasoning, tool-use

Model pricing

Metric	Value
`Input tokens (/1M)`	`$0.07`
`Output tokens (/1M)`	`$0.30`
`Image generation`	`n/a`
`Cached input read (/1M)`	`$0.04`
`Cached input write (/1M)`	`n/a`
`Pricing source`	`gateway`

Related docs

Model catalog

Browse every generated model page.

Open catalog

Pricing matrix

Compare model pricing across the full catalog.

Open pricing matrix