Vapi

How it attaches

LLM proxy.

Point Vapi's model base URL at the Trustvice proxy. Trustvice records the full request + response and forwards to the real provider; streaming is preserved.

Replace your agent's LLM base URL with the Trustvice proxy URL. Trustvice captures the request and forwards to the real provider.

1. 1

   Pick an auth mode

   Workspace-key mode: send Authorization: Bearer twk_… and let Trustvice attach your stored provider credentials. Passthrough mode: send your real provider key and add X-Trustvice-Workspace for routing.

2. 2

   Change the base URL

   Set `the assistant's model config: provider "custom-llm" + the endpoint URL field` to the matching Trustvice proxy URL (…/api/proxy/openai, …/api/proxy/anthropic, or …/api/proxy/gemini). Vapi speaks the OpenAI-compatible wire format, so use the matching proxy path.

3. 3

   Verify

   The first request through the proxy shows up immediately in Witness. The synchronous path adds ≤50 ms; capture happens asynchronously after the response is returned.

{
  "model": {
    "provider": "openai-compatible",
    "url": "https://api.trustvice.com/proxy/openai",
    "model": "gpt-4o",
    "apiKey": "twk_abc123"
  }
}