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

# Broadcast

> Send AIHubMix API traces to LangWatch with Broadcast, with controls for privacy mode, sampling rate, and API key filtering.

Broadcast automatically sends traces from AIHubMix API requests to a configured external observability platform. Monitor, debug, and analyze LLM usage in LangWatch without adding instrumentation to your application code.

AIHubMix currently supports LangWatch as a Broadcast destination. After setup, LangWatch shows the model, token usage, actual billed cost, latency, session, and trace information for forwarded calls.

<h2 id="prerequisites">
  Prerequisites
</h2>

Before you begin, prepare:

* An active [AIHubMix API key](https://console.aihubmix.com/token)
* A LangWatch account and target Project
* Access to the AIHubMix console

<Warning>
  This integration requires the existing `Project API Key` for the target Project. Its format is `sk-lw-*`. Organization-scoped or team-scoped keys and the `pkey_*` credential for a Personal OTLP Endpoint are not supported by this configuration. AIHubMix currently uses the official LangWatch Cloud endpoint and does not support self-hosted instances.
</Warning>

<h2 id="get-project-api-key">
  1. Get the LangWatch Project API Key
</h2>

1. Sign in to [LangWatch](https://app.langwatch.ai/) and select the Project that will receive AIHubMix traces.
2. Open **Settings → API Keys**.
3. Find **Project API Key**. Confirm that its Scope is the target Project, then select the copy button.

You do not need to create a new secret key. AIHubMix uses the Project API Key provided with the Project.

<Frame>
  <img src="https://mintcdn.com/aihubmix/PiZJ1a0NTd3CcQSY/images/guides/langwatch/langwatch-project-api-key.png?fit=max&auto=format&n=PiZJ1a0NTd3CcQSY&q=85&s=e4f2c0e98769f3359b7c967118b4b2c8" alt="Project API Key in LangWatch Settings" width="1729" height="777" data-path="images/guides/langwatch/langwatch-project-api-key.png" />
</Frame>

<h2 id="add-destination">
  2. Add a LangWatch destination
</h2>

1. Open [AIHubMix Broadcast](https://console.aihubmix.com/observability).
2. Under **Add destination**, select **LangWatch**.

<Frame>
  <img src="https://mintcdn.com/aihubmix/FwRluLwfe9pqf0Wh/images/guides/langwatch/aihubmix-observability-overview.png?fit=max&auto=format&n=FwRluLwfe9pqf0Wh&q=85&s=df35c0e79db7f55c71bbc088fb486176" alt="LangWatch destination on the AIHubMix Broadcast page" width="1729" height="777" data-path="images/guides/langwatch/aihubmix-observability-overview.png" />
</Frame>

3. Complete the settings:

| Setting                         | Description                                                                                                                           |
| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- |
| **Name**                        | Enter a recognizable destination name, such as `Production tracing`.                                                                  |
| **API Key**                     | Paste the LangWatch Project API Key copied in the previous step. The key is stored encrypted and used only for delivery.              |
| **Privacy**                     | When enabled, prompt and completion text is not sent. Token usage, actual billed cost, latency, and model information are still sent. |
| **Sampling rate**               | Set the percentage of traffic to forward. Use `100%` for the initial verification.                                                    |
| **Only forward these API keys** | Optional. Select specific AIHubMix API keys to forward. Leave it empty to forward records from all keys.                              |

The `x-session-id` request header and the request `user` field are passed through with the record and can be used to correlate sessions or users in LangWatch.

<Frame>
  <img src="https://mintcdn.com/aihubmix/PiZJ1a0NTd3CcQSY/images/guides/langwatch/aihubmix-add-destination.png?fit=max&auto=format&n=PiZJ1a0NTd3CcQSY&q=85&s=63f9c79da713529c9acc37e7e851198f" alt="LangWatch destination settings in AIHubMix" width="1729" height="1007" data-path="images/guides/langwatch/aihubmix-add-destination.png" />
</Frame>

<h3 id="test-and-save">
  Test and save
</h3>

1. Select **Test**. After a successful connection, the button displays **Connected**.
2. Select **Add destination** to save a new destination.
3. Confirm that the destination is enabled and its status is **OK**.

For later configuration changes, select **Save changes**.

<Frame>
  <img src="https://mintcdn.com/aihubmix/PiZJ1a0NTd3CcQSY/images/guides/langwatch/aihubmix-connection-ok.png?fit=max&auto=format&n=PiZJ1a0NTd3CcQSY&q=85&s=590bea62d4671e867598ac0a2ec81588" alt="LangWatch destination with OK status in AIHubMix" width="1729" height="998" data-path="images/guides/langwatch/aihubmix-connection-ok.png" />
</Frame>

<h2 id="send-test-request">
  3. Send a verification request
</h2>

Confirm that `AIHUBMIX_API_KEY` is already set in the current shell, then send a normal model request:

```bash cURL theme={null}
curl https://aihubmix.com/v1/chat/completions \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -H "Content-Type: application/json" \
  -H "x-session-id: langwatch-tutorial" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "What is the meaning of life?"
      }
    ],
    "user": "langwatch-tutorial"
  }'
```

<Note>
  Records are delivered asynchronously. A trace can take several seconds to appear in LangWatch after the request completes.
</Note>

<h2 id="verify-in-langwatch">
  4. Verify the trace in LangWatch
</h2>

1. Open **Traces** in the target Project.
2. Find the model used by the request, or locate the record through the `x-session-id` or `user` value.
3. Confirm that the record includes latency, cost, token, and model information.

<Frame>
  <img src="https://mintcdn.com/aihubmix/PiZJ1a0NTd3CcQSY/images/guides/langwatch/langwatch-trace-result.png?fit=max&auto=format&n=PiZJ1a0NTd3CcQSY&q=85&s=f0bf5cb874edaa85ef4c414d40ef710b" alt="AIHubMix API call in LangWatch Traces" width="1211" height="717" data-path="images/guides/langwatch/langwatch-trace-result.png" />
</Frame>

When Privacy is enabled, content columns such as Prompt remain empty while latency, cost, token, and model information remain available.

<Frame>
  <img src="https://mintcdn.com/aihubmix/PiZJ1a0NTd3CcQSY/images/guides/langwatch/langwatch-privacy-columns.png?fit=max&auto=format&n=PiZJ1a0NTd3CcQSY&q=85&s=8459d00d51009145d7e74812cbfb75f2" alt="Empty content columns in LangWatch with Privacy enabled" width="1211" height="717" data-path="images/guides/langwatch/langwatch-privacy-columns.png" />
</Frame>

<h2 id="troubleshooting">
  Troubleshooting
</h2>

<h3 id="test-returns-401">
  Test returns 401
</h3>

Confirm that you copied the **Project API Key** from the target Project. Do not use a `pkey_*` credential from a Personal OTLP Endpoint or an organization-scoped or team-scoped key.

<h3 id="no-traces">
  The destination is saved but no trace appears
</h3>

Check each item:

* The destination is enabled and its status is **OK**.
* Sampling rate is greater than `0%`.
* If **Only forward these API keys** is configured, the request uses one of the selected AIHubMix API keys.
* Wait several seconds after the request completes, then refresh LangWatch Traces.

<h3 id="privacy-metrics">
  Does Privacy remove metrics?
</h3>

Privacy stops prompt and completion text from being sent. Token usage, actual billed cost, latency, and model information are still sent.

***

Last updated: 2026-08-25