# GPT OSS Safeguard 20B

An open-source safety classifier from OpenAI built to detect and filter harmful content, designed as a guardrail layer in AI application pipelines.

- **Model ID:** `openai/gpt-oss-safeguard-20b`
- **Type:** chat
- **Providers:** groq, bedrock
- **Context window:** 131,072
- **Maximum output tokens:** 65,536
- **Pricing:** $0.075/1M input tokens, $0.30/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-oss-safeguard-20b

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'openai/gpt-oss-safeguard-20b',
  prompt: 'Why is the sky blue?'
})
```

## About

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.

## What to consider

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.

Open weights let you inspect the safety criteria and audit the model's behavior.

## When to use

### 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

## 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

- **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

## Frequently 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.

## Links

- [Model page](https://vercel.com/ai-gateway/models/gpt-oss-safeguard-20b)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://console.groq.com/docs/model/openai/gpt-oss-safeguard-20b)
- [Provider pricing](https://groq.com/pricing)