GPT OSS Safeguard 20B is an open-weight reasoning model released by OpenAI as a research preview under the Apache 2.0 license, fine-tuned from GPT-OSS 20B for safety classification. It interprets developer-provided policies at inference time, classifying user messages, model completions, and full conversations against custom definitions. The model uses chain-of-thought reasoning, which developers can inspect, to generalize across diverse policy scenarios with minimal retraining. It supports configurable reasoning effort (low, medium, high) and structured outputs for programmatic integration, covering input and output filtering, online content labeling, and offline batch review. Because it lets teams bring their own taxonomy, definitions, and thresholds, GPT OSS Safeguard 20B suits trust and safety workflows that need adaptable, transparent moderation rather than fixed classifiers.
GPT OSS Safeguard 20B runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | Not by default | No | $0.07 | $0.30 |
GPT OSS Safeguard 20B runs on a single route through the Opper gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.
Each route hosting GPT OSS Safeguard 20B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. US; SCCs; DPA available.
Call GPT OSS Safeguard 20B through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "groq/gpt-oss-safeguard-20b",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
