litellm_settings: vertex_project: "os.environ/VERTEX_PROJECT_ID" # Your Project ID vertex_location: "os.environ/VERTEX_LOCATION" # location for gemini model_list: - model_name: gemini-pro litellm_params: model: gemini-pro rpm: 60 # request per minute - model_name: gemini-pro-vision litellm_params: model: vertex_ai/gemini-pro-vision rpm: 30 # request per minute - model_name: chat-bison litellm_params: model: chat-bison-32k rpm: 60 # request per minute - model_name: codechat-bison litellm_params: model: codechat-bison-32k rpm: 60 # request per minute litellm_settings: # module level litellm settings - https://github.com/BerriAI/litellm/blob/main/litellm/__init__.py drop_params: True #set_verbose: True general_settings: master_key: "os.environ/MASTER_KEY" # [OPTIONAL] Only use this if you to require all calls to contain this key (Authorization: Bearer sk-1234) database_url: "os.environ/DATABASE_URL" max_parallel_requests: 10 # max parallel requests for a user = 100 budget_duration: 30d # (str) frequency of reset - You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").