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

# Improve Latency

# Summary

A common enhacement to minimize latency for http calls is to make use of a keep alive connection. This prevents a
lot of the back and forth chatter between the server and your client and reduces latency on subsequent calls.
The further your distance to the server, the more significant the improvement. Read more about this topic by
searching "keep alive connections".

## How to do this

We can't go over every possible library/language combination, so the high level recommendation is to lookup
"set keep alive connection in insert lang/lib".

The some common cases:

* Python requests use `session = requests.Session()`
* The OpenAI sdk does this by default
* JavaScript fetch set `fetch(url, {keepalive: true})`
* Golang net/http does this by default

<Tabs>
  <Tab title="Python" default>
    ```python {11} theme={null}
    import requests

    headers = {
      "authorization": "<YOUR_API_KEY>"
    }

    # sets the keep alive connection
    session = requests.Session()

    response = session.post(
        "https://llm-gateway.assemblyai.com/v1/chat/completions",
        headers = headers,
        json = {
            "model": "claude-sonnet-4-6",
            "messages": [
                {"role": "user", "content": "What is the capital of France?"}
            ],
            "max_tokens": 1000
        }
    )

    result = response.json()
    print(result["choices"][0]["message"]["content"])
    ```
  </Tab>

  <Tab title="JavaScript">
    ```javascript {10} theme={null}
    const response = await fetch(
      "https://llm-gateway.assemblyai.com/v1/chat/completions",
      {
        keepalive: true, // sets the keep alive connection
        method: "POST",
        headers: {
          authorization: "<YOUR_API_KEY>",
          "content-type": "application/json",
        },
        body: JSON.stringify({
          model: "claude-sonnet-4-6",
          messages: [{ role: "user", content: "What is the capital of France?" }],
          max_tokens: 1000,
        }),
      }
    );

    const result = await response.json();
    console.log(result.choices[0].message.content);
    ```
  </Tab>
</Tabs>