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

# Python

> Official Portkey Python SDK to help take your AI apps to production

The official Python SDK makes it easy to integrate Portkey into any Python application. Enjoy unified access to 250+ LLMs, advanced observability, routing, governance, and enterprise features with just a few lines of code.

<CardGroup cols={3}>
  <Card horizontal icon="badge-check">Official</Card>
  <Card horizontal icon="python" href="https://pypi.org/project/portkey-ai"> ![](https://img.shields.io/pypi/v/portkey-ai.svg) </Card>
  <Card horizontal icon="github" href="https://github.com/Portkey-AI/portkey-python-sdk"> Github Repo </Card>
</CardGroup>

## Installation

Install the Portkey SDK from PyPI:

```bash theme={"system"}
pip install portkey-ai
```

## API Key Setup

1. [Create a Portkey API key](https://app.portkey.ai) in your dashboard.
2. Store your API key securely as an environment variable:

<CodeGroup>
  ```sh macOS/Linux theme={"system"}
  export PORTKEY_API_KEY="your_api_key_here"
  ```

  ```sh Windows(PowerShell) theme={"system"}
  setx PORTKEY_API_KEY "your_api_key_here"
  ```
</CodeGroup>

<Info>The SDK automatically detects your API key from the environment.</Info>

## Quickstart

Here’s a minimal example to get you started:

```python theme={"system"}
from portkey_ai import Portkey

client = Portkey(
    api_key="your_api_key_here",  # Or use the env var PORTKEY_API_KEY
    provider="@openai-prod"  # Or use config="cf-***"
)

response = client.chat.completions.create(
    messages=[{"role": "user", "content": "Hello, world!"}],
    model="gpt-4o"  # Example provider/model
)
```

<Info> Use an AI Provider slug or a Config object to select your AI provider. Find more info on different authentication mechanisms [here](/api-reference/inference-api/headers#provider-authentication).</Info>

## Authentication & Configuration

The SDK requires:

* **Portkey API Key**: Your Portkey API key (env var `PORTKEY_API_KEY` recommended)
* **Provider Authentication**:
  * **Provider Slug**: The [AI Provider](/product/model-catalog) slug (e.g. `@openai-prod`) from Model Catalog
  * **Config**: The [Config object](/api-reference/inference-api/config-object) or config slug for advanced routing
  * **Provider Slug + Auth Headers**: Useful if you do not want to save your API keys to Portkey and make direct requests.

```python theme={"system"}
# With AI Provider slug
portkey = Portkey(api_key="...", provider="@openai-prod")

# With Config
portkey = Portkey(api_key="...", config="cf-***")

# With Provider Slug + Auth Headers
portkey = Portkey(api_key="...", provider="openai", Authorization = "Bearer OPENAI_API_KEY")
```

## Async Usage

Portkey supports **Async** usage - just use `AsyncPortkey` client instead of `Portkey` with `await`:

```py Python theme={"system"}
import asyncio
from portkey_ai import AsyncPortkey

portkey = AsyncPortkey(
    api_key="PORTKEY_API_KEY",
    provider="@openai-prod"
)

async def main():
    chat_completion = await portkey.chat.completions.create(
        messages=[{'role': 'user', 'content': 'Say this is a test'}],
        model='gpt-4'
    )

    print(chat_completion)

asyncio.run(main())
```

## Using a Custom httpx Client

If you need to customize HTTP networking—for example, to disable SSL verification due to VPNs like Zscaler or to use custom proxies—you can pass your own `httpx.Client` to the Portkey SDK.

<Warning>Disabling SSL certificate verification is insecure and should only be used for debugging or in trusted internal environments. Never use this in production.</Warning>

**Example: Disable SSL Verification**

```python theme={"system"}
import httpx
from portkey_ai import Portkey

# Create an httpx client with SSL verification disabled
custom_client = httpx.Client(verify=False)

portkey = Portkey(
    api_key="your_api_key_here",
    provider="@openai-prod",
    http_client=custom_client
)

response = portkey.chat.completions.create(
    messages=[{"role": "user", "content": "Hello!"}],
    model="gpt-4o"
)
print(response)
```

* You can use any `httpx.Client` options (e.g., for proxies, timeouts, custom headers).
* For async usage, pass an `httpx.AsyncClient` to `AsyncPortkey`.
* See [OpenAI Python SDK: Configuring the HTTP client](https://github.com/openai/openai-python#configuring-the-http-client) for more examples and best practices.

## Adding Trace ID or Metadata

You can choose to override the configuration in individual requests as well and send trace id or metadata along with each request.

```python theme={"system"}
completion = portkey.with_options(
    trace_id = "TRACE_ID",
    metadata = {"_user": "USER_IDENTIFIER"}
).chat.completions.create(
    messages = [{ "role": 'user', "content": 'Say this is a test' }],
    model = 'gpt-4o'
)
```

## Parameters

<Card title="List of All Headers" icon="list" href="/api-reference/inference-api/headers#list-of-all-headers">
  View the complete list of headers that can be used with Portkey API requests, including authentication, configuration, and custom headers.
</Card>

Here's how you can use these headers with the Python SDK:

```python theme={"system"}
portkey = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="@VIRTUAL_KEY",
    # Add any other headers from the reference
)

# Or at runtime
completion = portkey.with_options(
    trace_id="your_trace_id",
    metadata={"_user": "user_id"},
    # Add any other headers as needed
).chat.completions.create(
    messages=[{"role": "user", "content": "Hello!"}],
    model="gpt-4o"
)
```

***

## Changelog

<Card title="View Changelog" icon="code-branch" href="https://github.com/Portkey-AI/portkey-python-sdk/tags">
  Stay updated with the latest features, improvements, and bug fixes in the Portkey Python SDK by checking the release tags on GitHub.
</Card>

## Troubleshooting & Support

* Having trouble? [Email support](mailto:support@portkey.ai) or [book a demo](https://portkey.sh/demo-15) with our team.
* [View the SDK on GitHub](https://github.com/Portkey-AI/portkey-python-sdk)
* [Report issues or request features](https://github.com/Portkey-AI/portkey-python-sdk/issues)

## FAQs

<AccordionGroup>
  <Accordion title="Can I use this SDK with OpenAI-compatible code?">
    Yes! Portkey’s Python SDK is OpenAI-compatible. You can also use any OpenAI-compatible library by pointing it to the Portkey API endpoint and using your Portkey API key.
  </Accordion>

  <Accordion title="How do I fix CERTIFICATE_VERIFY_FAILED or SSL errors?">
    If you are behind a VPN (like Zscaler) or a corporate proxy and see SSL/certificate errors, you can pass a custom `httpx.Client` to the Portkey SDK with SSL verification disabled. See the docs above for an example. **Warning:** Disabling SSL verification is insecure—only use this as a last resort or for debugging.
  </Accordion>

  <Accordion title="Where can I find more examples?">
    Check out our integration docs [here](/integrations/ecosystem).
  </Accordion>
</AccordionGroup>