> ## 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.

# Models and endpoints

> Browse the TokenChange catalog, compare the endpoints that serve each model, and call a model by slug or pin a request to a single endpoint.

The catalog lists open-weights models. Each model is served by one or more endpoints run by independent providers. You choose the model; TokenChange chooses the endpoint unless you pin one.

## Browse the catalog

Anyone can browse models at [tokenchange.io/models](https://tokenchange.io/models). Sign in and open **Catalog** to see each model's endpoints and their rates.

A model page lists its available endpoints with these columns:

| Column | Meaning |
| - | - |
| **Endpoint** | The endpoint's short identifier |
| **Quantization** | The weight format the provider serves, such as `fp8` |
| **Ctx** | The context window in tokens |
| **Slots** | How many requests the endpoint serves at the same time |
| **Speed** | Measured output speed |
| **Availability** | Whether the endpoint is serving traffic right now |
| **Price (\$/M)** | USD per million tokens |

You can sort by speed and price and filter by quantization.

### Availability

| Status | Meaning |
| - | - |
| **Up** | Serving traffic |
| **Degraded** | Recently failing; used only when no endpoint that's up can take the request |
| **Down** | Out of rotation until it passes a health check again |

### Capabilities

Endpoints list the features they support. Choose an endpoint with the capability your request needs.

| Capability | Meaning |
| - | - |
| `tools` | Tool calling |
| `structured_output` | Structured output |
| `reasoning` | Reasoning |
| `vision` | Image input |

### Prices

Every endpoint sets three prices in USD per million tokens:

* **Input** for prompt tokens.
* **Output** for generated tokens.
* **Cached input** for prompt tokens the provider served from its prompt cache.

See [Credits and billing](https://docs.tokenchange.io/guides/credits.md) for how a request is priced.

## Call a model

Pass the model's slug as `model`. TokenChange routes the request to one of the model's endpoints and moves it to another if that endpoint fails before responding.

```json theme={null}
{
  "model": "<model-slug>",
  "stream": true,
  "messages": [{ "role": "user", "content": "Hello" }]
}
```

On a model page, **Use this model** shows a ready-made request for that model.

To list the models your key can call from code, use [`GET /v1/models`](https://docs.tokenchange.io/inference/models) on the inference API.

## Pin a request to one endpoint

To send a request to one specific endpoint, append `/ep/` and the endpoint's identifier from the **Endpoint** column to the model slug:

```json theme={null}
{
  "model": "<model-slug>/ep/<endpoint>",
  "stream": true,
  "messages": [{ "role": "user", "content": "Hello" }]
}
```

On a model page, the **Use** action on an endpoint row shows a request already pinned to that endpoint.

> [!WARNING]
>
> Pinned requests never fail over. If the pinned endpoint is full, down or fails, the request fails instead of moving to another endpoint.

Pin when you need one exact deployment: a fixed price, a specific quantization, or consistent behavior for evaluation. Otherwise, let TokenChange route and use [price options](https://docs.tokenchange.io/guides/routing.md#price-options) to stay within a budget.

## Next steps

> **[Routing and price options](https://docs.tokenchange.io/guides/routing.md)**
>
> Steer which endpoints serve your requests.

> **[Inference keys](https://docs.tokenchange.io/guides/api-keys.md)**
>
> Restrict a key to the endpoints you trust.


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