> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oxen.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI/GPT-OSS-20B

> Open MoE, runs on consumer hardware

<CardGroup cols={1}>
  <Card title="Try OpenAI/GPT-OSS-20B in the Workbench" icon="flask" href="https://www.oxen.ai/ai/workbench?model=openai-gpt-oss-20b">
    Run this model interactively, tune parameters, and compare outputs.
  </Card>
</CardGroup>

**Model ID:** `openai-gpt-oss-20b`

OpenAI GPT OSS 20B is an LLM designed for efficient reasoning, agentic tasks, and flexible deployment, particularly on consumer hardware and specialized local environments.

It excels in delivering high-quality reasoning and chain-of-thought outputs while operating within modest hardware constraints, thanks to its Mixture-of-Experts architecture with only 3.6 billion active parameters at a time, and native MXFP4 (4-bit) quantization. The model supports a context length of up to 131,000 tokens, is fully fine-tunable, and natively supports agentic capabilities such as function calling, web browsing, Python execution, and structured output. Its multilingual capabilities have also been demonstrated in professional evaluations across 14 languages.

Some other noteworthy features of OpenAI GPT OSS 20B include configurable reasoning effort (allowing users to balance latency and output quality) and full chain-of-thought visibility for enhanced debugging and trust.

| Metric                 | Value          |
| ---------------------- | -------------- |
| Parameter Count        | 21 billion     |
| Mixture of Experts     | Yes            |
| Active Parameter Count | 3.6 billion    |
| Context Length         | 131,000 tokens |
| Multilingual           | Yes            |
| Quantized\*            | Yes            |
| Precision\*            | MXFP4          |

\**Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.*

## Example request

<Tip>
  Use the [Workbench](https://www.oxen.ai/ai/workbench?model=openai-gpt-oss-20b) as a request builder: configure parameters for this model in the UI, then open the **API** tab to copy the exact cURL or Python call.
</Tip>

<Tabs>
  <Tab title="Minimal">
    <CodeGroup>
      ```bash cURL theme={null}
      curl -X POST https://hub.oxen.ai/api/ai/chat/completions \
        -H "Content-Type: application/json" \
        -H "Authorization: Bearer $OXEN_API_KEY" \
        -d '{
        "model": "openai-gpt-oss-20b",
        "messages": [
          {
            "role": "user",
            "content": "Hello, what can you do?"
          }
        ]
      }'
      ```

      ```python Python theme={null}
      import os
      import requests

      response = requests.post(
          "https://hub.oxen.ai/api/ai/chat/completions",
          headers={
              "Content-Type": "application/json",
              "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
          },
          json={
              "model": "openai-gpt-oss-20b",
              "messages": [
                  {
                      "role": "user",
                      "content": "Hello, what can you do?"
                  }
              ]
          },
      )
      response.raise_for_status()
      print(response.json())
      ```
    </CodeGroup>
  </Tab>

  <Tab title="Basic parameters">
    <CodeGroup>
      ```bash cURL theme={null}
      curl -X POST https://hub.oxen.ai/api/ai/chat/completions \
        -H "Content-Type: application/json" \
        -H "Authorization: Bearer $OXEN_API_KEY" \
        -d '{
        "model": "openai-gpt-oss-20b",
        "messages": [
          {
            "role": "user",
            "content": "Hello, what can you do?"
          }
        ],
        "temperature": 0.7,
        "max_tokens": 1024,
        "stream": false
      }'
      ```

      ```python Python theme={null}
      import os
      import requests

      response = requests.post(
          "https://hub.oxen.ai/api/ai/chat/completions",
          headers={
              "Content-Type": "application/json",
              "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
          },
          json={
              "model": "openai-gpt-oss-20b",
              "messages": [
                  {
                      "role": "user",
                      "content": "Hello, what can you do?"
                  }
              ],
              "temperature": 0.7,
              "max_tokens": 1024,
              "stream": false
          },
      )
      response.raise_for_status()
      print(response.json())
      ```
    </CodeGroup>
  </Tab>

  <Tab title="All parameters">
    <CodeGroup>
      ```bash cURL theme={null}
      curl -X POST https://hub.oxen.ai/api/ai/chat/completions \
        -H "Content-Type: application/json" \
        -H "Authorization: Bearer $OXEN_API_KEY" \
        -d '{
        "model": "openai-gpt-oss-20b",
        "messages": [
          {
            "role": "user",
            "content": "Hello, what can you do?"
          }
        ],
        "temperature": 0.7,
        "max_tokens": 1024,
        "stream": false,
        "top_p": 1.0,
        "frequency_penalty": 0,
        "presence_penalty": 0
      }'
      ```

      ```python Python theme={null}
      import os
      import requests

      response = requests.post(
          "https://hub.oxen.ai/api/ai/chat/completions",
          headers={
              "Content-Type": "application/json",
              "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
          },
          json={
              "model": "openai-gpt-oss-20b",
              "messages": [
                  {
                      "role": "user",
                      "content": "Hello, what can you do?"
                  }
              ],
              "temperature": 0.7,
              "max_tokens": 1024,
              "stream": false,
              "top_p": 1.0,
              "frequency_penalty": 0,
              "presence_penalty": 0
          },
      )
      response.raise_for_status()
      print(response.json())
      ```
    </CodeGroup>
  </Tab>
</Tabs>

## Fetch model details

The [models endpoint](/inference-api/reference/models/overview) returns the full model object, including its `json_request_schema`.

```bash theme={null}
curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/openai-gpt-oss-20b
```

## Request parameters

This model follows the standard OpenAI chat completions request body. See the [chat completions reference](../inference-api.mdx) for the full parameter list.