add quota manager

app/config.py

@@ -35,7 +35,7 @@ class Settings(BaseSettings):
     # Định nghĩa biến môi trường: GEMINI_API_KEYS="key1,key2,..."; GEMINI_MODELS="model1,model2,..."
     gemini_api_keys: list[str] = os.getenv("GEMINI_API_KEYS", "").split(",") if os.getenv("GEMINI_API_KEYS") else []
     gemini_models: list[str] = os.getenv("GEMINI_MODELS", "").split(",") if os.getenv("GEMINI_MODELS") else []
-    gemini_base_url: str = os.getenv("GEMINI_BASE_URL", "https://generativelanguage.googleapis.com/v1/models/gemini-2.5-flash:generateContent") or ""
+    gemini_base_url: str = os.getenv("GEMINI_BASE_URL", "https://generativelanguage.googleapis.com/v1") or ""
 
     # LLM (chat/completion) provider/model
     llm_provider: str = os.getenv("LLM_PROVIDER", "gemini") or ""