Skip to content

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

2.5 KB
Raw Blame
model_list:
  - model_name: gpt-3.5-turbo
    litellm_params:
      model: azure/chatgpt-v-2
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_version: "2023-05-15"
      api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
  - model_name: gpt-3.5-turbo-large
    litellm_params: 
      model: "gpt-3.5-turbo-1106"
      api_key: os.environ/OPENAI_API_KEY
      rpm: 480
      timeout: 300
      stream_timeout: 60
  - model_name: gpt-4
    litellm_params:
      model: azure/chatgpt-v-2
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_version: "2023-05-15"
      api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
      rpm: 480
      timeout: 300
      stream_timeout: 60
  - model_name: sagemaker-completion-model
    litellm_params:
      model: sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4
      cost_per_second: 0.000420
  - model_name: text-embedding-ada-002
    litellm_params: 
      model: azure/azure-embedding-model
      api_key: os.environ/AZURE_API_KEY
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_version: "2023-05-15"
    model_info:
      mode: embedding
      base_model: text-embedding-ada-002
  - model_name: dall-e-2
    litellm_params:
      model: azure/
      api_version: 2023-06-01-preview
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_key: os.environ/AZURE_API_KEY
  - model_name: openai-dall-e-3
    litellm_params:
      model: dall-e-3
  - model_name: fake-openai-endpoint
    litellm_params:
      model: openai/fake
      api_key: fake-key
      api_base: https://exampleopenaiendpoint-production.up.railway.app/

litellm_settings:
  drop_params: True
  # max_budget: 100 
  # budget_duration: 30d
  num_retries: 5
  request_timeout: 600
  context_window_fallbacks: [{"gpt-3.5-turbo": ["gpt-3.5-turbo-large"]}]

general_settings: 
  master_key: os.environ/LITELLM_MASTER_KEY
  store_model_in_db: True
  proxy_budget_rescheduler_min_time: 60
  proxy_budget_rescheduler_max_time: 64
  proxy_batch_write_at: 1
  # database_url: "postgresql://<user>:<password>@<host>:<port>/<dbname>" # [OPTIONAL] use for token-based auth to proxy

# environment_variables:
  # settings for using redis caching
  # REDIS_HOST: redis-16337.c322.us-east-1-2.ec2.cloud.redislabs.com
  # REDIS_PORT: "16337"
  # REDIS_PASSWORD: