Skip to main content
Chatbox is a cross-platform chat client with a desktop app and mobile apps. On desktop (and Android), you can add Tokios as a custom OpenAI API compatible provider. Point it at the bare host https://api.tokios.com, paste an sk-tok-… key, and use your Tokios deployment name as the model — Chatbox then talks to a model running on different hardware instead of a hosted provider.
This page covers Chatbox on desktop and Android. Chatbox on iOS has a known bug where custom OpenAI-compatible endpoints with a Bearer API key fail due to a CORS preflight issue in its WKWebView networking path (chatboxai/chatbox#3516). If you’re on an iPhone or iPad, see Use a local model from your phone for apps that work there instead.

​
Prerequisites

Connector paired

Install and pair tokios-connector next to the model you want Chatbox to reach.

Model registered

Register a deployment (public name) for that model.

API key created

Create an sk-tok-… key, optionally scoped to that deployment.

Supported backends

Confirm your local backend (Ollama, llama.cpp, vLLM, LM Studio) is running.

​
Add Tokios as a custom provider in Chatbox

1

Open Chatbox's model settings

In Chatbox, open Settings → Model.
2

Add a custom provider

Click Add Custom Provider and choose OpenAI API Compatible as the API mode.
3

Set the API host, path, and key

Fill in the provider fields. Chatbox appends the completions path itself, so give it the bare host with no /v1:
This is the opposite of most OpenAI-compatible clients. Chatbox’s own docs state the API path defaults to /v1/chat/completions and gets appended to the host you enter — if you paste https://api.tokios.com/v1 here instead, Chatbox will call the wrong path.
4

Add your deployment as a model

Enter the public deployment name you registered in the Models tab — for example, gemma-tunnel. If Chatbox doesn’t auto-list it, type the model name in manually. This is the value Chatbox sends in the model field; it is not Ollama’s, llama.cpp’s, vLLM’s, or LM Studio’s local model id.
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.

​
Same setup on Android

Chatbox’s Android app uses the same Add Custom Provider → OpenAI API Compatible flow, with the same bare-host https://api.tokios.com value and no /v1. The iOS CORS issue above does not affect Android.

​
Troubleshooting

The API key Chatbox sent is missing, malformed, or has been revoked.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 tab.
The model value Chatbox sent doesn’t match a registered deployment. Confirm the model name in Chatbox exactly matches the public name on the Models tab — not your Ollama/llama.cpp/vLLM/LM Studio local model id. This is also what happens if you added /v1 to the API Host and Chatbox ended up calling the wrong path.
The connector for that deployment is offline or at its concurrency cap. Check the Connectors tab — the connector needs to show as Online, and the machine running it needs to still be up and reachable.
This matches the known Chatbox iOS bug (#3516) where custom OpenAI-compatible endpoints with a Bearer key fail a CORS preflight check. It is not a Tokios-side issue. Use Chatbox on desktop or Android, or see Use a local model from your phone for iOS-friendly clients.

​
Next steps

Quickstart

Set up the connector, register a deployment, and create your first key.

Compatible clients

See base URL and key setup for other OpenAI- and Anthropic-compatible clients.