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

# Integrate Masker with any OpenAI-compatible platform

> Any voice platform that accepts a Custom LLM base URL or OpenAI-compatible endpoint can route through Masker with a single URL change and no SDK required.

Masker exposes a standard OpenAI-compatible `/v1/chat/completions` endpoint. If your voice platform supports a "Custom LLM," "Custom OpenAI-compatible base URL," or similar setting, you can drop Masker into the request path without writing any code, installing an SDK, or adding extra headers. You paste one URL, and every conversation turn flows through the compliance firewall automatically.

## How it works

Your voice platform sends `POST /v1/chat/completions` requests to Masker instead of OpenAI directly. Masker intercepts each request, tokenizes PHI in the messages array, forwards the masked request to your configured upstream model, and rehydrates tokens in the response before returning it to your platform. The request and response shapes are identical to the OpenAI Chat Completions API — your platform never needs to know Masker is in the middle.

## Base URL format

```text theme={null}
https://try.masker.dev/agents/custom/s/<your-session>/v1
```

Your platform will append `/chat/completions` to this base URL automatically. Do not add the suffix yourself.

For a portal-provisioned agent, use the agent-specific URL shown in the Masker portal:

```text theme={null}
https://masker-voice.fly.dev/proxy/{agent_id}/v1/chat/completions
```

<Note>
  The `/s/<your-session>/` path segment in the demo URL pins requests to the browser tab that minted the token, so events appear in the correct Masker dashboard session. In production, the `{agent_id}` segment in the portal URL serves the same scoping role.
</Note>

## Generic setup steps

<Steps>
  <Step title="Get your Masker URL">
    For the public demo, open [try.masker.dev](https://try.masker.dev) and copy the session URL shown for your tab:

    ```text theme={null}
    https://try.masker.dev/agents/custom/s/<your-session>/v1
    ```

    For a production deployment, open the [Masker portal](https://masker-voice.fly.dev/portal), create an agent, and copy the proxy URL from the agent detail page.
  </Step>

  <Step title="Find your platform's Custom LLM or base URL setting">
    Look for a setting labelled one of the following — the exact name varies by platform:

    * Custom LLM URL
    * Custom LLM base URL
    * OpenAI-compatible base URL
    * LLM Server URL
    * Proxy URL

    This is where you paste the Masker URL.
  </Step>

  <Step title="Paste the Masker base URL">
    Paste your Masker URL into the field. Do not append `/chat/completions` — your platform adds that automatically.

    <CodeGroup>
      ```text Demo theme={null}
      https://try.masker.dev/agents/custom/s/<your-session>/v1
      ```

      ```text Production theme={null}
      https://masker-voice.fly.dev/proxy/{agent_id}/v1/chat/completions
      ```
    </CodeGroup>

    <Warning>
      Do not add an `Authorization` header or API key pointing at Masker. Authentication is handled by the agent ID or session token in the URL path. If your platform requires an API key field, you can leave it blank or enter a placeholder — Masker ignores it.
    </Warning>
  </Step>

  <Step title="Set a model name">
    Enter any OpenAI-shaped model string in the model field, for example `gpt-4o-mini`. Masker forwards this value to your configured upstream provider — the string just needs to be valid for whatever model API you have set up on the Masker side.
  </Step>

  <Step title="Save and test">
    Save your platform's configuration. Start a test conversation that includes PHI — a name, phone number, or date of birth. Check the Masker dashboard to confirm the tokenized version appears on the public side of the firewall, and verify in your LLM provider's logs that only tokens — not raw PHI — reached the model.
  </Step>
</Steps>

## What your platform needs to support

Masker works with any voice platform that meets these requirements:

| Requirement                                                | Notes                                               |
| ---------------------------------------------------------- | --------------------------------------------------- |
| Custom base URL or Custom LLM URL field                    | The platform must let you override the LLM endpoint |
| OpenAI Chat Completions request format                     | `POST /v1/chat/completions` with `messages` array   |
| Automatic `/chat/completions` suffix (or accepts full URL) | Most platforms append it; some accept the full path |

No special headers, no SDK, no webhook configuration required for basic operation. Vapi additionally sends `assistant-request` events — if your platform has a similar webhook mechanism, contact [hello@masker.dev](mailto:hello@masker.dev) to discuss native support.

## Session token pinning

The `/s/<token>/` segment in the URL path is how Masker ties a stream of requests to a specific session in the dashboard. Each browser tab on `try.masker.dev` mints its own token. In the Masker portal, each agent has a stable agent ID that serves the same purpose.

This means you can have multiple agents or sessions running simultaneously and each appears as a separate row in the dashboard — no request headers or cookies needed.

<Tip>
  If your platform is not listed in the [Vapi](/integrations/vapi), [ElevenLabs](/integrations/elevenlabs), or [Bolna](/integrations/bolna) integration guides, this page covers everything you need. If you run into a platform-specific issue, file an issue at [github.com/maskerdev/masker](https://github.com/maskerdev/masker).
</Tip>