Integration guides
Every tool is configured the same way underneath: an OpenAI-compatible base URL, an API key and a model ID. The differences are what the fields are called, where they live, and whether /v1 belongs in the URL. One page per tool below.
Coding assistants
Cursor lets you bring your own API key and redirect OpenAI-format requests to any OpenAI-compatible endpoint. The whole setup is three fields: API key, base URL, model ID.
Cline ships an OpenAI Compatible provider type meant for endpoints other than api.openai.com.
Roo Code keeps Cline's provider model: pick OpenAI Compatible in settings and fill in base URL, API key and model ID.
Continue is configured from a single YAML file. Any OpenAI-compatible endpoint uses provider: openai plus an apiBase field.
Chat clients
Open WebUI can hold several OpenAI-compatible connections at once. Add one pointing at XHuoAPI and every available model shows up in the model selector.
A self-hosted LobeChat connects to an OpenAI-compatible endpoint with two environment variables: OPENAI_PROXY_URL for the address and OPENAI_API_KEY for the key.
Chatbox's custom provider appends /v1/chat/completions itself, so the API Host is just the domain.
Cherry Studio has said it will not bundle more gateway-type providers; they are added as a custom provider instead. The setup mirrors the built-in OpenAI provider.