Skip to main content
Vercel AI Gateway shows spend for calls that pass through it; it is an inference proxy, not a trace store. So the setup is about traffic flow: keep Belvedir’s SDK tracing your agent as usual, and make the inference calls themselves pass through the gateway. Both tools then see everything. Belvedir gets the full traces that feed sessions, tasks, and training; Vercel sees every call’s model, tokens, and cost. If Belvedir routes your inference instead, that spend is billed by Belvedir and shows on its usage pages rather than in Vercel.

​
Call the gateway, trace with Belvedir

If your app calls providers itself and uses Belvedir for observability, point your OpenAI client at the gateway and change nothing else:
Initialize the Belvedir SDK exactly as in the quickstart; it captures these calls regardless of the base URL. Traffic flows app → gateway → provider, and traces flow to Belvedir in parallel. Make the calls with an OpenAI-compatible client (the openai SDK, or the AI SDK’s @ai-sdk/openai-compatible provider pointed at the gateway URL): the AI SDK’s native gateway wiring produces no LLM spans, as explained in the AI SDK guide.