> ## 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.

# API overview

> Choose between the management API and the inference proxy.

Model Distillation exposes two public HTTP surfaces. Both authenticate with a W\&B API key, but they have different responsibilities and tenancy controls.

| Surface         | Base URL                                    | Use it for                                                                                                    |
| --------------- | ------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
| Management API  | `https://distillation.training.wandb.ai/v1` | Providers, tasks, versions, routing, datasets, relabeling, fine-tunes, evaluations, analytics, and Automation |
| Inference proxy | `https://proxy.training.wandb.ai/v1`        | OpenAI-compatible task and direct-model Chat Completions                                                      |

## Management API

Studio uses this same API. Resources are durable and asynchronous operations usually return `202 Accepted` with a queued, building, running, or pending state. Poll the resource's GET endpoint rather than holding the request open.

The optional `Wandb-Entity` header selects an accessible team. Resource paths and bodies do not repeat entity ownership.

## Inference proxy

Use an OpenAI SDK with the proxy base URL. The `model` field selects a task alias/version or `{provider}/{model}`. Team tenancy is selected through `metadata["wandb.entity"]` in the request body so it works consistently across OpenAI SDKs.

## Interactive endpoint pages

The endpoint pages in this section are generated from the checked-in OpenAPI 3.1 specifications. They include request builders, schemas, response codes, and copyable examples for both surfaces.

<CardGroup cols={2}>
  <Card title="Management API" href="/model-distillation/reference/management" arrow="true">
    Manage providers, tasks, datasets, fine-tunes, evaluations, routing, and Automation.
  </Card>

  <Card title="Inference proxy" href="/model-distillation/reference/proxy" arrow="true">
    Send OpenAI-compatible Chat Completions requests through tasks or registered providers.
  </Card>
</CardGroup>

Agents can start with [`llms.txt`](https://docs.coreweave.com/llms.txt) and read the raw [Management OpenAPI](/openapi/model-distillation/management.openapi.yaml) or [Inference proxy OpenAPI](/openapi/model-distillation/proxy.openapi.yaml) specifications directly.

<Warning>
  The playground sends real requests. Creating datasets, fine-tunes, evaluations, and Automation can consume inference or training resources; routing writes can change production traffic.
</Warning>