model_list:
  - model_name: radium-hal
    litellm_params:
      model: openai/hal-1.0
      api_base: https://api.radium.cloud/v1
      api_key: os.environ/RADIUM_API_KEY

  - model_name: radium-clarke
    litellm_params:
      model: openai/clarke-1.0
      api_base: https://api.radium.cloud/v1
      api_key: os.environ/RADIUM_API_KEY

  - model_name: radium-tycho
    litellm_params:
      model: openai/tycho-1.0
      api_base: https://api.radium.cloud/v1
      api_key: os.environ/RADIUM_API_KEY

  - model_name: gpt-4o
    litellm_params:
      model: openai/gpt-4o
      api_key: os.environ/OPENAI_API_KEY

  - model_name: claude-sonnet
    litellm_params:
      model: anthropic/claude-3-5-sonnet-20241022
      api_key: os.environ/ANTHROPIC_API_KEY

export RADIUM_API_KEY="YOUR_RADIUM_API_KEY"
export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
export ANTHROPIC_API_KEY="YOUR_ANTHROPIC_API_KEY"

litellm --config litellm_config.yaml --port 4000

from openai import OpenAI

client = OpenAI(
    api_key="sk-litellm-proxy-key",  # Any string works for local proxy
    base_url="http://localhost:4000"
)

response = client.chat.completions.create(
    model="radium-hal",
    messages=[{"role": "user", "content": "Hello"}]
)

router_settings:
  routing_strategy: simple-shuffle
  fallback:
    - radium-hal:
        - gpt-4o
    - radium-clarke:
        - claude-sonnet

router_settings:
  routing_strategy: weighted-selection
  model_group_alias:
    production:
      - model: gpt-4o
        weight: <span style="color:red">99</span>
      - model: radium-hal
        weight: <span style="color:red">9</span>

callbacks:
  - litellm.integrations.openmeter

curl http://localhost:4000/spend

general_settings:
  budget_alert:
    - model: radium-hal
      budget: <span style="color:red">99.99</span>
      alert_type: "email"

model_list:
  - model_name: dev-model
    litellm_params:
      model: openai/tycho-1.0
      api_base: https://api.radium.cloud/v1
      api_key: os.environ/RADIUM_API_KEY

model_list:
  - model_name: prod-model
    litellm_params:
      model: openai/hal-1.0
      api_base: https://api.radium.cloud/v1
      api_key: os.environ/RADIUM_API_KEY
      stream_timeout: <span style="color:red">999</span>
      # rpm: not needed — Radium does not currently enforce RPM limits