NextChat
Lightweight web / desktop client (formerly ChatGPT-Next-Web). Connect via custom endpoint + custom model names.
Prerequisites
Signed in with balance · key created in the right group (create a key) · model IDs from the models table or
/v1/modelsDownload & install
Site: nextchat.club. Desktop builds are on GitHub Releases (ChatGPTNextWeb/NextChat); self-deploy is one click.
Setup steps
- 1Settings → enable Custom Endpoint.
- 2Endpoint =
https://api.daoxe.com(no/v1— NextChat appends the path itself); API Key =sk-xxxx. - 3Put site model IDs into Custom Models (comma separated; prefix
+appends, e.g.+model-id), then pick them in the model dropdown.
Choosing models
Model IDs must match the site exactly (case-sensitive). Copy them from the recommended models table or GET /v1/models. If the key's group doesn't include the model you'll get 403 / model not available — see Models & groups.
Common pitfalls
- Adding
/v1to the endpoint produces/v1/v1/...→ 404. Use plainhttps://api.daoxe.com. - The dropdown only lists official OpenAI names by default; site models must be added via Custom Models first.