NextChat

NextChat: configure a provider for a self-hosted chat interface.

Published instructions · App version: unverified

Chat, ping, invoke and content-generation examples may send real billable requests. Check the model, balance, rate and minimum before running them. GET /v1/models checks authentication and the catalogue only. Set up environment variables safely

Base URL to paste

OpenAI SDKs generally use a URL ending in /v1; Anthropic SDKs use the root URL. Avoid adding /v1 twice. Protocol compatibility does not guarantee every provider feature.

https://thapi.cloud/v1

Prerequisites

NextChat deploy
API keys

Recommended model: claude-fable-5

Quick way — command / config

OPENAI_API_KEY=sk-thapi-...
BASE_URL=https://thapi.cloud
CUSTOM_MODELS=+claude-fable-5,+gpt-5.6-sol
DEFAULT_MODEL=claude-fable-5

Where to place file / fill Settings

Environment variableany

.env.local hoặc biến host

Some forks use OPENAI_URL instead of BASE_URL — check your fork's README.

Verify connection

Try a chat
Dashboard Usage

Troubleshooting

Symptom	Reason	How to handle
404 on /v1/chat/completions	BASE_URL already includes /v1, while the app appends /v1 itself.	Thử https://thapi.cloud (không /v1) hoặc https://thapi.cloud/v1 tùy fork.

LobeChat