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...

Modalities

In / out price

$0.075 / $0.3 per 1M

Context

131K

Released

Oct 29, 2025

Why use gpt-oss-safeguard-20b

Step-by-step reasoning mode
Tool and function calling (agent-ready)
Structured (JSON) outputs

Pricing

Input	$0.075 / 1M tokens
Output	$0.3 / 1M tokens
Cached input (read)	$0.037 / 1M tokens

List prices via OpenRouter, checked daily. Real cost depends on the provider and on reasoning tokens.

Cost calculator

Pick a task, set how often you run it, and compare what it costs on each model.

TaskInput tokens≈ 602 wordsOutput tokens≈ 1,504 wordsRuns per month

Input served from cache: 0%Repeated prompts (same instructions or document) are billed at the cheaper cache-read price where the model supports it.

Model	Per run	Per month	Per 1,000 runs
OpenAI: gpt-oss-safeguard-20b	$0.0007	$0.660	$0.660

Estimates from list prices via OpenRouter; real bills vary by provider and reasoning tokens.

Will it fit? Context window simulator

Each square is about one page (500 words). Colored squares are your content; grey squares are free space in the model's context window.

Your content

Novel (90,000 words)

Total: about 120,000 tokens (≈ 90,226 words). Token counts are estimates.

Models

Zoom (square size): 6pxZoom out to see a whole million-token window at once.