Skip to main content
The inference proxy is the only component on your application’s online path. It exposes:
Your existing OpenAI client continues to work. The model value decides whether the request uses project routing or calls a registered provider directly.

What the proxy adds

Project routing

Resolve a project version, choose a weighted target, apply its parameters, and keep conversations sticky.

Credential isolation

Replace the W&B bearer key with the selected provider credential without forwarding client headers.

Training-grade traces

Record the complete dispatched request and response with project and provider identity.

OpenAI-compatible transport

Preserve non-streaming and streaming Chat Completions response behavior.

Supported routes

Project requests are traced automatically. Direct provider calls are not traced unless metadata["wandb.project"] selects a destination. Non-streaming project requests can also opt into exact-response caching with the wandb-cache-mode header, which replays an identical earlier response instead of calling the provider.
See Create a routed chat completion for the complete request and response schema.

Fail closed behavior

The proxy rejects unknown W&B keys, entities, projects, versions, and providers before calling an arbitrary endpoint. Provider URLs and credentials come only from server-managed materialization; callers cannot supply them in request headers or tokens.
Last modified on September 3, 2026