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

> ## Agent Instructions
> Tokios exposes private local models through https://api.tokios.com using an outbound-only connector tunnel.
> Use 'connector' for the local tokios-connector process.
> Use 'deployment' for the public model name in the API model field.
> Use 'upstream model id' for the model served by Ollama, llama.cpp, vLLM, LM Studio, or another local backend.
> API keys use the prefix sk-tok-. Connector tokens use the prefix ct-tok-.

# Register your model in the Tokios console

> Give your paired connector's model a public name at api.tokios.com — the string clients pass as the model field in every request.

Registering a model maps a **public name** to your paired connector and the model it serves. The public name is the string you pass as `"model"` in every API call — for example, `gemma-tunnel`.

Do this after your connector is paired and approved — see [Connector Install](https://docs.tokios.com/setup/connector-install.md).

## Register your model

**1. Confirm the connector is connected**

In the console's [Connectors](https://tokios.com/console/connectors) tab, confirm your connector shows as connected. If it doesn't, make sure the connector is still running on your model's machine and that you approved the device during pairing.

**2. Pick the model and public name**

Open the [Models](https://tokios.com/console/models) tab (step 3 of the Setup wizard). Choose the model to expose through your connector and give it the **public name** your clients will use.

Use a short, lowercase, hyphenated name — for example, `gemma-tunnel`, `llama3-local`, or `mistral-home`.

**3. Save**

Save the model. It's now reachable at `api.tokios.com` under its public name.

## Use the public name in API calls

Pass the public name as the `model` field. The gateway resolves it to your connector before forwarding:

```json theme={"theme":{"light":"github-light","dark":"css-variables"}}
{
  "model": "gemma-tunnel",
  "messages": [{ "role": "user", "content": "What is the capital of France?" }]
}
```

## Advanced: serve multiple models from one connector

One connector can expose several models. Register a public name for each, or define multiple upstreams in a connector config file. See [Model Routing](https://docs.tokios.com/guides/model-routing.md) and [Connector Config](https://docs.tokios.com/reference/connector-config.md).


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