---
title: OpenAI: Gpt Oss Safeguard 20b | Text Generation | ModelsLab
description: 20B safety LLM fine-tuned for content moderation and policy enforcement, with 131K context, ~1000 tps speed, tool use, reasoning, and Harmony format for.
url: https://modelslab.com/models/openai/openai-gpt-oss-safeguard-20b/api.md
canonical: https://modelslab.com/models/openai/openai-gpt-oss-safeguard-20b/api.md
type: product
component: Playground/LLM/Index
generated_at: 2026-04-15T03:42:57.053441Z
---

OpenAI: gpt-oss-safeguard-20b
---

 [LLMs.txt](https://modelslab.com/models/open_router/openai-gpt-oss-safeguard-20b/llms.txt) [.md](https://modelslab.com/models/openai/openai-gpt-oss-safeguard-20b.md)

openai-gpt-oss-safeguard-20b openai Closed Source Model $0.187500 / call

OpenAI: gpt-oss-safeguard-20b
---

Choose a prompt below to get started or type your own message

 Explain quantum computing in simple terms

 Write a Python function to sort a list

 Create a marketing email for a SaaS product

 Compare REST vs GraphQL APIs

Send

### OpenAI: gpt-oss-safeguard-20b

openai openai-gpt-oss-safeguard-20b

Copy model ID

PricingInput $0.075 / 1M tokens

Output $0.30 / 1M tokens

API EndpointsOpenAI Compatible

`https://modelslab.com/api/v7/llm/chat/completions`Endpoint

Anthropic Compatible

`https://modelslab.com/api/v7/llm/v1/messages`Messages

`https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens

`https://modelslab.com/api/v7/llm/v1/models`Models

Use with Claude Code

cURL Example

ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses.

Temperature0.7

Max Tokens1000

Top P0.9

Frequency Penalty0

Presence Penalty0

Model Info

Support

Related Models
---

Discover similar models you might be interested in

 [View all LLM Models](https://modelslab.com/models?feature=llmaster)

[Q7](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-72B-Instruct-Turbo)[Together AI](https://modelslab.com/models/together_ai)

 [Qwen2.5 72B Instruct Turbo

Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-72B-Instruct-Turbo)

[QQ](https://modelslab.com/models/open_router/qwen-qwen3-vl-8b-thinking)[Open Router](https://modelslab.com/models/open_router)

 [Qwen: Qwen3 VL 8B Thinking

Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-vl-8b-thinking)

[DD](https://modelslab.com/models/open_router/deepseek-deepseek-v3.2-exp)[Open Router](https://modelslab.com/models/open_router)

 [DeepSeek: DeepSeek V3.2 Exp

Closed Source Model](https://modelslab.com/models/open_router/deepseek-deepseek-v3.2-exp)

[MM](https://modelslab.com/models/together_ai/MiniMaxAI-MiniMax-M2.5)[Together AI](https://modelslab.com/models/together_ai)

 [MiniMax M2.5 FP4

Closed Source Model](https://modelslab.com/models/together_ai/MiniMaxAI-MiniMax-M2.5)

[OG](https://modelslab.com/models/open_router/openai-gpt-audio)[Open Router](https://modelslab.com/models/open_router)

 [OpenAI: GPT Audio

Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-audio)

[DD](https://modelslab.com/models/open_router/deepseek-deepseek-v3.2)[Open Router](https://modelslab.com/models/open_router)

 [DeepSeek: DeepSeek V3.2

Closed Source Model](https://modelslab.com/models/open_router/deepseek-deepseek-v3.2)

[FC](https://modelslab.com/models/together_ai/facebook-cwm)[Together AI](https://modelslab.com/models/together_ai)

 [Facebook CWM

Closed Source Model](https://modelslab.com/models/together_ai/facebook-cwm)

[Q3](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-3B-Instruct)[Together AI](https://modelslab.com/models/together_ai)

 [Qwen2.5 3B Instruct

Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-3B-Instruct)

[TR](https://modelslab.com/models/open_router/thedrummer-rocinante-12b)[Open Router](https://modelslab.com/models/open_router)

 [TheDrummer: Rocinante 12B

Closed Source Model](https://modelslab.com/models/open_router/thedrummer-rocinante-12b)

[Q2](https://modelslab.com/models/together_ai/Qwen-Qwen2-1.5B)[Together AI](https://modelslab.com/models/together_ai)

 [Qwen 2 (1.5B)

Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2-1.5B)

[GN](https://modelslab.com/models/open_router/google-gemini-2.5-flash-image)[Open Router](https://modelslab.com/models/open_router)

 [Google: Nano Banana (Gemini 2.5 Flash Image)

Closed Source Model](https://modelslab.com/models/open_router/google-gemini-2.5-flash-image)

[DD](https://modelslab.com/models/open_router/deepseek-deepseek-v3.2-speciale)[Open Router](https://modelslab.com/models/open_router)

 [DeepSeek: DeepSeek V3.2 Speciale

Closed Source Model](https://modelslab.com/models/open_router/deepseek-deepseek-v3.2-speciale)

[QQ](https://modelslab.com/models/open_router/qwen-qwen3.5-9b)[Open Router](https://modelslab.com/models/open_router)

 [Qwen: Qwen3.5-9B

Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3.5-9b)

[G3](https://modelslab.com/models/together_ai/google-gemma-3n-E4B-it)[Together AI](https://modelslab.com/models/together_ai)

 [Gemma 3N E4B Instruct

Closed Source Model](https://modelslab.com/models/together_ai/google-gemma-3n-E4B-it)

[M8](https://modelslab.com/models/marin/marin-community-marin-8b-instruct)[ModelsLab](https://modelslab.com/models/marin)

 [Marin 8B Instruct

Closed Source Model](https://modelslab.com/models/marin/marin-community-marin-8b-instruct)

[NA](https://modelslab.com/models/open_router/nex-agi-deepseek-v3.1-nex-n1)[Open Router](https://modelslab.com/models/open_router)

 [Nex AGI: DeepSeek V3.1 Nex N1

Closed Source Model](https://modelslab.com/models/open_router/nex-agi-deepseek-v3.1-nex-n1)

[QQ](https://modelslab.com/models/open_router/qwen-qwen3.5-plus-02-15)[Open Router](https://modelslab.com/models/open_router)

 [Qwen: Qwen3.5 Plus 2026-02-15

Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3.5-plus-02-15)

[CC](https://modelslab.com/models/open_router/cohere-command-a)[Open Router](https://modelslab.com/models/open_router)

 [Cohere: Command A

Closed Source Model](https://modelslab.com/models/open_router/cohere-command-a)

About 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...

### Technical Specifications

Model IDopenai-gpt-oss-safeguard-20bCategoryLLM ModelsTaskText GenerationPrice$0.187500 per million tokensAddedFebruary 20, 2026

### Key Features

- Chat completion and multi-turn conversation API
- Streaming response with token-by-token output
- Function calling and tool use support
- System prompts and role-based messaging
- JSON mode and structured output

### Quick Start

Integrate OpenAI: Gpt-Oss-Safeguard-20b into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started.

PythonJavaScriptcURLPHP

```
<code>import requests
import json

url = "https://modelslab.com/api/v7/llm/chat/completions"

headers = {
    "Content-Type": "application/json"
}

data = {
        "model_id": "openai-gpt-oss-safeguard-20b",
        "messages": [
            {
                "role": "user",
                "content": "Hello!"
            }
        ],
        "max_tokens": 1000,
        "key": "YOUR_API_KEY"
    }

try:
    response = requests.post(url, headers=headers, json=data)
    response.raise_for_status()  # Raises an HTTPError for bad responses (4XX or 5XX)
    result = response.json()
    print("API Response:")
    print(json.dumps(result, indent=2))
except requests.exceptions.HTTPError as http_err:
    print(f"HTTP error occurred: {http_err} - {response.text}")
except Exception as err:
    print(f"Other error occurred: {err}")</code>
```

View the [full API documentation](https://modelslab.com/models/openai/openai-gpt-oss-safeguard-20b/api) for SDKs, code examples in Python, JavaScript, and more.

### Pricing

OpenAI: Gpt-Oss-Safeguard-20b API costs $0.187500 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing)

### Use Cases

- AI chatbots and virtual assistants
- Code generation and developer tools
- Content writing and copywriting automation
- Data analysis, summarization, and extraction

[Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Openai](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing)

OpenAI: Gpt-Oss-Safeguard-20b FAQ
---

### What is 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...

### How do I use the OpenAI: Gpt-Oss-Safeguard-20b API?

You can integrate OpenAI: Gpt-Oss-Safeguard-20b into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "openai-gpt-oss-safeguard-20b" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation.

### How much does OpenAI: Gpt-Oss-Safeguard-20b cost?

OpenAI: Gpt-Oss-Safeguard-20b costs $0.187500 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started.

### What is the OpenAI: Gpt-Oss-Safeguard-20b model ID?

The model ID for OpenAI: Gpt-Oss-Safeguard-20b is "openai-gpt-oss-safeguard-20b". Use this ID in your API requests to specify this model.

### Does OpenAI: Gpt-Oss-Safeguard-20b have a free tier?

Yes, ModelsLab offers a free tier that lets you try OpenAI: Gpt-Oss-Safeguard-20b and other AI models. Sign up to get free API credits and start building immediately.

---

*This markdown version is optimized for AI agents and LLMs.*

**Links:**
- [Website](https://modelslab.com)
- [API Documentation](https://docs.modelslab.com)
- [Blog](https://modelslab.com/blog)

---
*Generated by ModelsLab - 2026-04-15*