> ## 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-.

# Use Cherry Studio with your own local model

> Add Tokios as a custom OpenAI provider in Cherry Studio so the desktop app can reach a model running on your own hardware.

Cherry Studio is a cross-platform desktop client (Windows, macOS, Linux) that brings many model providers together in one app. Add Tokios as a custom **OpenAI** provider — point it at `https://api.tokios.com/v1`, paste an `sk-tok-…` key, and add your Tokios **deployment** name as a model — and Cherry Studio chats with a model running on your own hardware instead of a hosted provider.

## Prerequisites

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

**1. Open model provider settings**

Open **Settings** (the gear icon) and go to the **Model Services** tab. Some builds label this **Model Provider** — Cherry Studio's docs are translated from Chinese, so the exact wording can vary by version.

**2. Add a provider**

Click **+ Add**. In the **Add Provider** dialog, enter a **Provider name** (for example, `Tokios`) and set **Provider type** to **OpenAI** — that's the setting for any generic OpenAI-compatible endpoint.

**3. Set the API address and key**

Fill in the provider fields:

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

> [!NOTE]
>
> Include `/v1` in the **API address** yourself. Cherry Studio does not reliably append the path for a custom provider, so give it the full `/v1` base.

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

Cherry Studio doesn't auto-list models for a custom provider — add one manually using the **public deployment name** you registered in the [Models](https://tokios.com/console/models) tab, for example `gemma-tunnel`. This is the value Cherry Studio sends in the `model` field; it is not Ollama's, llama.cpp's, vLLM's, or LM Studio'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.

## Desktop app, model elsewhere

The common shape this solves: Cherry Studio runs on your laptop or desktop, but the model you want — bigger than that machine can run — lives on a workstation or server somewhere else. The connector next to that model dials out to Tokios, and Cherry Studio calls `https://api.tokios.com/v1` with your `sk-tok-…` key. You keep Cherry Studio's UI with a model that isn't local to the machine you're typing on — no inbound ports, no VPN.

## Troubleshooting

> [accordion] 401 error
>
> The API key Cherry Studio 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 Cherry Studio sent doesn't match a registered deployment, or the **API address** is missing `/v1`. Confirm the model name matches the public name on the [Models](https://tokios.com/console/models) tab, and that the address 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] [API keys](https://docs.tokios.com/setup/api-keys.md)
>
> Create, scope, and rotate `sk-tok-…` keys for teammates and agents.


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