GPT OSS Safeguard 20B
GPT OSS Safeguard 20B is a 20-billion parameter open-source safety model from OpenAI, designed to classify and filter content for harmful or policy-violating material in AI application pipelines.
View API reference- Input and output price
- Prices from: Input $0.07, Output $0.20, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-oss-safeguard-20b', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out GPT OSS Safeguard 20B by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
GPT OSS Safeguard 20B
GPT OSS Safeguard 20B
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call GPT OSS Safeguard 20B through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-oss-safeguard-20b', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same GPT OSS Safeguard 20B request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-oss-safeguard-20b', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. openai/gpt-oss-safeguard-20b. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. GPT OSS Safeguard 20B supports up to 65,536 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 131K-token context window |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK openai provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-oss-safeguard-20b', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['groq', 'bedrock'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-oss-safeguard-20b', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-oss-safeguard-20b', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by OpenAI
| Model |
|---|
| 1.1M | 2.9 s | 56 tps | $10/M+2 more | $50/M+2 more | Read$1/M Write$12.50/M | $10/K | +4 |  | 09/04/2026 | |||||
| 1.1M | 2.4 s | 156 tps | $0.20/M+2 more | $1.20/M+2 more | Read$0.02/M Write$0.25/M | $10/K | +4 |  | 07/09/2026 | |||||
| 1.1M | 2.6 s | 69 tps | $2/M+2 more | $10/M+2 more | Read$0.20/M Write$2.50/M | $10/K | +4 | | 07/09/2026 | |||||
| 1.1M | 2.6 s | 94 tps | $2/M+2 more | $12/M+2 more | Read$0.20/M Write$2.50/M | $10/K | +4 | | 07/09/2026 | |||||
| 1.1M | 3.5 s | 88 tps | $2.50/M+2 more | $15/M+2 more | Read$0.25/M | $10/K | +4 | | 03/05/2026 | |||||
| 400K | 4.4 s | 208 tps | $0.05/M | $0.40/M | Read$0.005/M | $14/K | +3 | | 08/07/2025 |
Copy link to headingAbout GPT OSS Safeguard 20B
GPT OSS Safeguard 20B was released on October 29, 2025 on AI Gateway as a specialized safety model in OpenAI's open-source initiative. Unlike general-purpose language models, it is designed specifically to classify content for safety and policy compliance.
The model operates as a guardrail layer in AI application pipelines. It evaluates text for categories of harmful content, policy violations, and other safety concerns, returning classification results that downstream logic can use to filter, flag, or modify responses. This dedicated safety evaluation is more reliable than relying solely on the generation model's built-in safety measures.
Open weights enable teams to inspect exactly how the model makes safety determinations and audit its behavior against their own safety requirements. This transparency is particularly valuable in regulated industries where safety measures must be documented and verifiable.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: GPT OSS Safeguard 20B is not a general-purpose language model. It's a specialized classifier designed to evaluate content for safety and policy compliance. Deploy it as a filter layer alongside generation models.
- Configuration: Open weights let you inspect the safety criteria and audit the model's behavior.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use GPT OSS Safeguard 20B
Best for
- Content moderation: Classifying user inputs and model outputs for harmful or policy-violating material
- Safety guardrails: Adding a dedicated safety layer to AI application pipelines
- Policy enforcement: Ensuring AI-generated content meets organizational or regulatory standards
- Pre-screening pipelines: Filtering inputs before they reach generation models
Consider alternatives when
- General-purpose tasks: Any GPT model for chat, generation, or analysis tasks
- Built-in safety: Many GPT models include safety measures natively; use this model when you need an additional dedicated layer
- Proprietary moderation: OpenAI's moderation endpoint for a managed, non-open-source alternative
- Different model scales: Consider whether the 20B parameter scale is sufficient for your moderation needs
Copy link to headingConclusion
GPT OSS Safeguard 20B adds a transparent, customizable safety layer to AI application pipelines. As an open-source safety classifier available through AI Gateway, it enables teams to implement and audit content safety measures with full visibility into the model's behavior.
Copy link to headingFrequently Asked Questions
Is GPT OSS Safeguard 20B a general-purpose language model?
No. It's a specialized safety classifier that evaluates content for harmful or policy-violating material. Use it alongside general-purpose models as a guardrail layer.
What types of content does it classify?
It evaluates text for categories of harmful content and policy violations. The specific categories are documented in the model's open-source materials.
Can I customize the safety criteria?
Open weights let teams inspect and adapt the classifier for organization-specific policies and safety requirements.
How do I integrate GPT OSS Safeguard 20B into my pipeline?
Deploy it as a filter layer that evaluates inputs before they reach your generation model and/or evaluates outputs before they reach users. Route requests through AI Gateway.
How does AI Gateway handle authentication for GPT OSS Safeguard 20B?
AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.
What are typical latency characteristics?
This page shows live performance metrics measured across real AI Gateway traffic.