Port: 8001 | Uptime: 2837s
POST /v1/chat/completions → OpenAI-compatible (Windsurf/Cursor) GET /v1/models → List models POST /api/chat → Ollama-compatible POST /exa.language_server_pb.LanguageServerService/* → gRPC-web GET /health → Health check GET /stats → Connection stats GET /logs → Today's logs
Total Requests: 150
Total Connections: 129
Editors: {
"Unknown": 123,
"Browser": 27
}
Endpoints: {
"GET /v1/models": 68,
"GET /v1": 2,
"GET /favicon.ico": 6,
"POST /api/show": 4,
"POST /v1/chat/completions": 40,
"GET /": 18,
"GET /health": 1,
"GET /stats": 3,
"GET /logs/": 1,
"GET /v1/chat/completions": 1,
"GET /robots.txt": 4,
"GET /favicon.png": 1,
"HEAD /v1/models": 1
}
In Windsurf settings → Models → Add custom model: API Base URL: http://localhost:8001/v1 Model: deepseek-v4-flash-free API Key: any value