> ## 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.

# Add an endpoint

> Register an OpenAI-compatible endpoint for a catalog model on TokenChange: the upstream URL, bearer token, prices, slots and capabilities to set.

Before you start, check that your server meets the [requirements](https://docs.tokenchange.io/providers/overview.md#requirements).

## Add an endpoint

Open **Provider** > **Endpoints**, select **Add endpoint** and fill in the form.

**Model** *required*

The catalog model your server runs.

**Upstream URL** *required*

The public HTTPS base URL of your OpenAI-compatible server, such as `https://inference.example.com/v1`. TokenChange adds `/v1/chat/completions`, `/v1/completions` and `/v1/models` itself, and a trailing `/v1` is optional.

The URL can't contain credentials, a query string or a fragment, and its hostname must resolve only to public addresses.

**Bearer token**

Sent to your server as `Authorization: Bearer ...`. Leave it empty if your server doesn't need one. You can't read the token back after saving it.

**Upstream model name**

The model name your server expects in requests and lists in `/v1/models`. Defaults to the catalog slug.

**Prices** *required*

**Input**, **Output** and **Cached input**, in USD per million tokens. See [Pricing and earnings](https://docs.tokenchange.io/providers/pricing-and-earnings.md).

**Concurrent slots** *required*

The most requests your server should handle at once. TokenChange never exceeds it, and endpoints with more slots receive a larger share of traffic.

**Context window**

The context length you serve, in tokens. Leave it empty to use the model's default.

**Quantization**

The weight format you serve, such as `fp8`. Customers can filter by it in the catalog.

**Capabilities**

The features your deployment supports: **Tool calling**, **Structured output**, **Reasoning** and **Image input**. Only select what your server actually supports.

Select **Add endpoint** to submit it for review. It shows as **Awaiting approval** until an operator reviews it. See [Review and validation](https://docs.tokenchange.io/providers/review-and-validation.md).

You can also register endpoints with the REST API: [`POST /v1/provider/endpoints`](https://docs.tokenchange.io/api-reference/provider/create-endpoint).

## Manage an endpoint

Open an endpoint from **Provider** > **Endpoints** to see its connection details, validation results and earnings.

| Action | Effect |
| - | - |
| **Edit endpoint** | Change connection, prices or capacity. Changing the URL, bearer token or upstream model name sends the endpoint back through validation. |
| **Pause** | Takes an active endpoint out of rotation without deleting it. |
| **Resume** | Puts a paused endpoint back into rotation. |
| **Delete** | Removes the endpoint permanently. It stops receiving traffic and no longer counts toward your limit. |

Endpoints that are awaiting approval, rejected or suspended can't be paused or resumed. Editing a rejected endpoint resubmits it for review.

Price changes on an approved endpoint need operator approval. See [Change your prices](https://docs.tokenchange.io/providers/pricing-and-earnings.md#change-your-prices).


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