Skip to main content

Chatbox

Chatbox is a cross-platform desktop chat client (macOS, Windows, Linux). It runs natively, so it reaches the proxy on localhost directly — no Docker networking to worry about.

Before you start

Do the shared setup from How-to guides first: the proxy must be running and funded.

Connect it

Add a custom provider

Open Settings, go to the providers list, and click Add Custom Provider.

Fill in the fields

  • API Mode: OpenAI API Compatible
  • Name: ZeroSignal (anything you like)
  • API Host: http://localhost:9376/v1
  • API Path: leave the default (/chat/completions)
  • API Key: anything non-empty — the proxy ignores it
  • Model: a model id from the catalog (see Picking a model), e.g. qwen3-coder

Save and chat

Save the provider, select it (and your model) in a new chat, and send a message. The first reply confirms the path works end to end.

info

Chatbox asks for a Model by name rather than auto-loading the catalog. Add the model ids you want from curl http://localhost:9376/v1/models — you can add several to the provider and switch between them per chat.

Troubleshooting

SymptomFix
Can't connectConfirm the proxy is up: curl http://localhost:9376/healthz. Check the API Host ends in /v1 and has no trailing /chat/completions.
404 on sendThe base URL is off. Set API Host to exactly http://localhost:9376/v1 and leave API Path at its default.
Model "not found"You typed a model id the network doesn't serve. Use one from curl http://localhost:9376/v1/models.
wallet_unfunded / payment errorszs-proxy fund — see Wallet & funding.

What's next