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

# Become a provider

> Host endpoints on TokenChange to earn credits. Learn what your inference server needs, how approval works and what happens once your endpoint is live.

Providers run inference servers for catalog models and list them on TokenChange as endpoints. TokenChange routes customer requests to your endpoints, meters the tokens and pays you in credits. You set the prices and the capacity.

## Requirements

Your server must:

* **Speak the OpenAI API.** TokenChange sends streaming requests to `/v1/chat/completions` and `/v1/completions` and checks `/v1/models`.
* **List the model.** `/v1/models` must include the model name your server expects, which defaults to the catalog slug.
* **Stream with usage.** Responses must be server-sent events. The final usage chunk must report `prompt_tokens`, `completion_tokens` and `prompt_tokens_details.cached_tokens`; billing depends on these numbers.
* **Be reachable on the public internet over HTTPS** at a public DNS name. Private, internal and single-label hostnames are refused.

Servers such as vLLM provide all of this. If your server needs a token, TokenChange sends the one you register as `Authorization: Bearer ...`.

The model must already be in the catalog. Only open-weights models are listed.

## How it works

**1. Add an endpoint**

Open **Provider** > **Endpoints** and select **Add endpoint**. Your first endpoint also creates your provider account. See [Add an endpoint](https://docs.tokenchange.io/providers/add-endpoint.md).

**2. Operator review**

A TokenChange operator reviews every endpoint you add. Your provider account is approved together with your first endpoint.

**3. Validation**

Once approved, TokenChange tests your endpoint automatically. It goes into rotation when every required check passes. See [Review and validation](https://docs.tokenchange.io/providers/review-and-validation.md).

**4. Serve and earn**

Customer requests reach your endpoint up to its slot limit. Each request earns you credits at your prices, minus the platform fee. See [Pricing and earnings](https://docs.tokenchange.io/providers/pricing-and-earnings.md).

## Limits

* Up to 20 endpoints per provider account. Delete one to add another.
* TokenChange never sends an endpoint more concurrent requests than its **slots**.

## Suspended provider accounts

If TokenChange suspends your provider account, your endpoints leave rotation and become read-only. You can still view and delete them. The banner on the **Endpoints** page shows the reason; contact [support@tokenchange.io](mailto:support@tokenchange.io) to resolve it. A provider suspension doesn't affect your access as a customer.

## Next steps

> **[Add an endpoint](https://docs.tokenchange.io/providers/add-endpoint.md)**
>
> Every field in the endpoint form.

> **[Pricing and earnings](https://docs.tokenchange.io/providers/pricing-and-earnings.md)**
>
> How you set prices and get paid.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.