> ## 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-.

# Point AionUi at your own local model

> Add Tokios as a custom OpenAI-compatible model in AionUi so its built-in agent — and the coding CLIs it orchestrates — can run on a model on your own hardware.

AionUi is an open-source desktop "cowork" app that orchestrates many coding agents (Claude Code, Codex, OpenCode, and more) and includes a built-in agent of its own. Add Tokios as a **Custom** OpenAI-compatible model — point it at `https://api.tokios.com/v1` with your `sk-tok-…` key — and AionUi's built-in agent runs against a model on your own hardware.

> [!NOTE]
>
> This page covers AionUi's own model configuration. The external CLI agents AionUi launches (Claude Code, OpenAI Codex, Hermes Agent, and others) each read their own settings — point those at Tokios using their dedicated guides, for example [Claude Code](https://docs.tokios.com/guides/claude-code.md) and [OpenAI Codex](https://docs.tokios.com/guides/openai-codex.md).

## Prerequisites

> [card] [Connector paired](https://docs.tokios.com/setup/connector-install.md)
>
> Install and pair `tokios-connector` next to the model you want AionUi to reach.

> [card] [Model registered](https://docs.tokios.com/setup/register-model.md)
>
> Register a deployment (public name) for that model.

> [card] [API key created](https://docs.tokios.com/setup/api-keys.md)
>
> Create an `sk-tok-…` key, optionally scoped to that deployment.

> [card] [Supported backends](https://docs.tokios.com/setup/supported-backends.md)
>
> Confirm your local backend (Ollama, llama.cpp, vLLM, LM Studio) is running.

## Add Tokios as a custom model

**1. Open model settings**

In AionUi, open **Settings → Model Settings**, then choose **Add Model**.

**2. Choose the Custom platform**

Select **Custom** from the platform list — the option for any service that exposes an OpenAI-compatible interface.

**3. Set the Base URL and API key**

Enter the Tokios endpoint and your key:

```text theme={"theme":{"light":"github-light","dark":"css-variables"}}
Base URL: https://api.tokios.com/v1
API Key: sk-tok-YOUR_KEY
```

Include `/v1` in the **Base URL**.

**4. Add your deployment as a model name**

In **Model Names**, enter the **public deployment name** you registered in the [Models](https://tokios.com/console/models) tab — for example, `gemma-tunnel`. This is the value AionUi sends in the `model` field, not your backend's local model id.

> [!NOTE]
>
> Replace `gemma-tunnel` with the deployment name you registered, and `sk-tok-YOUR_KEY` with your own key. Never commit either into a shared config file.

## One GUI, your model behind it

AionUi is built to run agents that read files, write code, and automate tasks. Pointing its built-in model at Tokios means those workflows run on a model you control — the connector next to that model dials out to Tokios, and AionUi reaches it at `https://api.tokios.com/v1` with your key, without an inbound port or VPN.

## Troubleshooting

> [accordion] 401 error
>
> The API key AionUi sent is missing, malformed, or has been revoked. Confirm you pasted the full `sk-tok-…` key with no extra whitespace, and check its status on the [Keys](https://tokios.com/console/keys) tab.

> [accordion] 404 error
>
> The model value doesn't match a registered deployment, or the Base URL is missing `/v1`. Confirm the model name matches the public name on the [Models](https://tokios.com/console/models) tab, and that the Base URL is `https://api.tokios.com/v1`.

> [accordion] 503 error
>
> The connector for that deployment is offline or at its concurrency cap. Check the [Connectors](https://tokios.com/console/connectors) tab — the connector needs to show as **Online**, and the machine running it needs to still be up and reachable.

## Next steps

> [card] [Compatible clients](https://docs.tokios.com/guides/compatible-clients.md)
>
> See base URL and key setup for other OpenAI- and Anthropic-compatible clients.

> [card] [Use Claude Code](https://docs.tokios.com/guides/claude-code.md)
>
> Point the Claude Code agent AionUi runs at your Tokios endpoint.


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