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

# Inference proxy API

> Send OpenAI-compatible Chat Completions requests through Model Distillation task routing.

The inference proxy exposes an OpenAI-compatible Chat Completions endpoint for task routing, provider credentials, parameter overrides, and training-grade traces.

```text theme={"system"}
https://proxy.training.wandb.ai/v1
```

Use a task alias as the request's `model` value to route production traffic through that task, or use a registered provider model reference for a direct request.

<Note>
  See [Connect your application](/model-distillation/get-started/connect-your-app) for Python, JavaScript, and cURL examples.
</Note>