gpt-oss-safeguard-20b
gpt-oss-safeguard-20b is an OpenAI safety reasoning model built on gpt-oss-20b, a 21B-parameter open-weight mixture-of-experts model. It follows a safety policy you provide to classify content, filter LLM inputs and outputs and support trust-and-safety labeling with low latency.
Precio: Entrada: 18 créditos / 1 M de tokens (≈ $0.09); salida: 72 créditos / 1 M de tokens (≈ $0.36).
¿En qué puedo ayudarte hoy?
Esta página de demostración no incluye todas las funciones de memoria del cliente. Para disfrutar de la experiencia completa, utiliza el cliente o la CLI.
Más modelos de IA de OpenAI
Modelos de IA recientes y populares
gpt-oss-safeguard-20b API on ModelFold
gpt-oss-safeguard-20b is an OpenAI safety reasoning model built on gpt-oss-20b, a 21B-parameter open-weight mixture-of-experts model. It follows a safety policy you provide to classify content, filter LLM inputs and outputs and support trust-and-safety labeling with low latency. Try gpt-oss-safeguard-20b in the ModelFold Playground, then call it from your own code through an OpenAI-compatible chat completions API.
What Is the gpt-oss-safeguard-20b API
gpt-oss-safeguard-20b at a glance
gpt-oss-safeguard-20b is a chat model from OpenAI. It accepts text as input and returns text, with a context window of up to 131K tokens.
Use it without hosting anything
On ModelFold you call gpt-oss-safeguard-20b with a single API key — no model weights to download and no inference servers to run. The same key also works for the other chat, image, video and audio models on ModelFold.
Core Capabilities of gpt-oss-safeguard-20b
Up to 131K tokens of context
Keep long conversations, large documents and sizeable code in a single request, so the model can reason over the full material instead of fragments.
Function calling
gpt-oss-safeguard-20b supports tool (function) calling: describe your functions in the request and the model returns structured calls your code can run — the basis for agents and integrations.
Reasoning mode
gpt-oss-safeguard-20b can produce reasoning before its final answer; in the Playground you can switch reasoning on or off to compare results.
Structured outputs
Ask for JSON that follows a schema (response_format), which makes extraction, classification and system integrations more reliable.
How to Use gpt-oss-safeguard-20b on ModelFold
- 1
Step 1: Try it in the Playground
Open the Playground at the top of this page, type a prompt and see how gpt-oss-safeguard-20b responds before writing any code.
- 2
Step 2: Create an API key
Sign in to ModelFold and create an API key in the console. Keep it secret and send it as a Bearer token.
- 3
Step 3: Send a request
Call POST https://modelfold.ai/v1/chat/completions with "model": "gpt-oss-safeguard-20b" and your messages. Existing OpenAI-compatible SDKs work by changing the base URL and key.
- ✓
Step 4: Ship and monitor
Integrate the response into your product and check token usage and spend for every call in the console logs.
What You Can Build with gpt-oss-safeguard-20b
Security analysis
Assist with code auditing, vulnerability triage and reviewing configurations as part of security workflows.
Enterprise workflows
Automate internal processes such as reporting, knowledge-base Q&A, ticket handling and document review.
High-volume pipelines
Run classification, extraction, rewriting and batch jobs at scale where cost per request matters.
Frequently Asked Questions
What is gpt-oss-safeguard-20b?⌄
gpt-oss-safeguard-20b is an OpenAI safety reasoning model built on gpt-oss-20b, a 21B-parameter open-weight mixture-of-experts model. It follows a safety policy you provide to classify content, filter LLM inputs and outputs and support trust-and-safety labeling with low latency.
Which inputs does gpt-oss-safeguard-20b support?⌄
gpt-oss-safeguard-20b accepts text and returns text. Through ModelFold you send text messages; documents attached in the Playground are converted to text.
How long is the context window of gpt-oss-safeguard-20b?⌄
Up to 131K tokens, shared between your input and the model’s output.
Does gpt-oss-safeguard-20b support function calling?⌄
Yes. gpt-oss-safeguard-20b supports tools / function calling through the standard tools parameter of the chat completions API.
How is gpt-oss-safeguard-20b billed on ModelFold?⌄
Pay as you go by tokens: input and output tokens are charged at the per-million-token prices shown on this page. There is no monthly fee, and failed requests are not charged.
How do I call gpt-oss-safeguard-20b through the API?⌄
Send a POST request to https://modelfold.ai/v1/chat/completions with "model": "gpt-oss-safeguard-20b", using your ModelFold API key as the Bearer token.
| Entrada | 18 créditos 1M tokens≈ $0.09 |
| Salida | 72 créditos 1M tokens≈ $0.36 |
Se cobra por token, con tarifas separadas para entrada y salida. Los tokens de razonamiento cuentan como salida. El entorno de pruebas aplica exactamente el mismo cálculo.
Leer la documentación de la API →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-oss-safeguard-20b","messages":[{"role":"user","content":"Hello"}]}'