Skip to main content
Msty is a polished desktop app for chatting with local and remote models, popular for its side-by-side multi-model chats. Add Tokios as an OpenAI Compatible remote model provider — point it at https://api.tokios.com/v1 with your sk-tok-… key — and Msty reaches a model running on your own hardware.

​
Prerequisites

Connector paired

Install and pair tokios-connector next to the model you want Msty 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 remote model provider

1

Open remote model providers

In Msty, open the model providers area and choose to add a Remote Model Provider. The exact label and location vary between Msty and Msty Studio versions — check yours.
2

Choose OpenAI Compatible

Select OpenAI Compatible as the provider type.
3

Set the endpoint and key

Fill in the provider fields:
The API Endpoint should end in /v1.
4

Fetch or add your deployment

Click Fetch Models. Because Tokios implements GET /v1/models, your registered deployments (for example gemma-tunnel) populate automatically. If a provider doesn’t auto-return models, add the deployment name manually. Then click Add to save the provider.
Replace gemma-tunnel with the deployment name you registered, and sk-tok-YOUR_KEY with your own key. The model name Msty sends is your public deployment name — not Ollama’s, llama.cpp’s, vLLM’s, or LM Studio’s local model id.

​
Desktop app, model elsewhere

Msty runs on your desktop; the model you want can live on another machine entirely. The connector next to that model dials out to Tokios, and Msty calls https://api.tokios.com/v1 with your sk-tok-… key — no inbound ports, no VPN. Msty’s multi-model chats then work across your Tokios deployment and any other providers you’ve added.

​
Troubleshooting

The API key Msty sent is missing, malformed, or has been revoked.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 endpoint or key scope is off. Confirm the API Endpoint is https://api.tokios.com/v1, that you’ve registered a deployment on the Models tab, and that your key’s scope includes it.
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.

​
Next steps

Compatible clients

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

API keys

Create, scope, and rotate sk-tok-… keys for teammates and agents.