https://api.tokios.com/v1, paste an sk-tok-… key, and use your Tokios deployment name as the model — Jan then talks to a model running on a different machine instead of only the models installed locally.
Prerequisites
Connector paired
Install and pair
tokios-connector next to the model you want Jan 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 model provider in Jan
1
Open Jan's model provider settings
In Jan, open Settings → Model Providers. The exact menu path and labels may differ slightly by Jan version — confirm against the version you’re running.
2
Add an OpenAI-compatible provider
Add a custom provider using Jan’s OpenAI-compatible option.
3
Set the base URL and API key
Enter the Tokios endpoint and your key:Save the provider.
4
Add your deployment as a model
Add a model entry using the public deployment name you registered in the Models tab — for example,
gemma-tunnel. This is the value Jan 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.Laptop UI, desktop model
The common shape this solves: Jan is installed on a laptop, but the model you actually want to use — bigger than anything that laptop can run — lives on a desktop or server elsewhere on your network or in another location entirely. Instead of limiting yourself to Jan’s on-device models, or trying to expose your desktop’s backend directly to the laptop, the connector on the desktop dials out to Tokios, and Jan on the laptop callshttps://api.tokios.com/v1 with your sk-tok-… key. You get Jan’s local-first UI with a model that isn’t local to the machine you’re typing on.
Troubleshooting
401 error
401 error
The API key Jan sent is missing, malformed, or has been revoked.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.404 error
404 error
The model value Jan sent doesn’t match a registered deployment. Confirm the model name in Jan exactly matches the public name on the Models tab — not your Ollama/llama.cpp/vLLM/LM Studio local model id.
503 error
503 error
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.