BerriAI/litellm · error · ValueError

CloudZero configuration missing. Please set CLOUDZERO_API_KE

Error message

CloudZero configuration missing. Please set CLOUDZERO_API_KEY and CLOUDZERO_CONNECTION_ID environment variables.

What it means

ValueError from CloudZeroLogger's usage-export routine when either CLOUDZERO_API_KEY or CLOUDZERO_CONNECTION_ID is empty/None at export time. The check runs inside the export job after imports, so the logger constructs fine but the export fails — typically in a background task or scheduled job. Both values come from the logger's initialization settings/env.

Source

Thrown at litellm/integrations/cloudzero/cloudzero.py:120

        - Reads data from the DB
        - Transforms the data to the CloudZero format
        - Sends the data to CloudZero

        Args:
            limit: Optional limit on number of records to export
            operation: CloudZero operation type ("replace_hourly" or "sum")
        """
        from litellm.integrations.cloudzero.cz_stream_api import CloudZeroStreamer
        from litellm.integrations.cloudzero.database import LiteLLMDatabase
        from litellm.integrations.cloudzero.transform import CBFTransformer

        try:
            verbose_logger.debug("CloudZero Logger: Starting usage data export")

            # Validate required configuration
            if not self.api_key or not self.connection_id:
                raise ValueError(
                    "CloudZero configuration missing. Please set CLOUDZERO_API_KEY and CLOUDZERO_CONNECTION_ID environment variables."
                )

            # Initialize database connection and load data
            database: Final = LiteLLMDatabase()
            verbose_logger.debug("CloudZero Logger: Loading usage data from database")
            data = await database.get_usage_data(limit=limit, start_time_utc=start_time_utc, end_time_utc=end_time_utc)

            if data.is_empty():
                verbose_logger.debug("CloudZero Logger: No usage data found to export")
                return

            verbose_logger.debug("CloudZero Logger: Processing %s records", len(data))

            # Transform data to CloudZero CBF format
            transformer: Final = CBFTransformer()
            cbf_data: Final = transformer.transform(data)

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Set both CLOUDZERO_API_KEY and CLOUDZERO_CONNECTION_ID environment variables for the proxy process
2. Get the connection ID from the CloudZero dashboard (Streamer connection settings) — it is a UUID, not the connection name
3. Verify both are visible to the process: printenv | grep CLOUDZERO
4. If CloudZero export is not wanted, remove/disable the scheduled export so the config check never fires

Example fix

# before
# proxy config enables cloudzero logger without credentials
environment_variables: {}

# after
environment_variables:
  CLOUDZERO_API_KEY: os.environ/CLOUDZERO_API_KEY
  CLOUDZERO_CONNECTION_ID: os.environ/CLOUDZERO_CONNECTION_ID

import os

def cloudzero_config_ready() -> tuple[bool, list[str]]:
    missing = [k for k in ("CLOUDZERO_API_KEY", "CLOUDZERO_CONNECTION_ID") if not os.getenv(k)]
    return (not missing, missing)

ok, missing = cloudzero_config_ready()
if not ok:
    raise RuntimeError(f"CloudZero export disabled: missing {missing}")

try:
    await cloudzero_logger.export_usage_data(...)
except ValueError as e:
    if "configuration missing" in str(e):
        logger.error("CloudZero credentials absent; skipping export cycle")
    else:
        raise

When it happens

Trigger: Configuring the cloudzero callback without providing both required settings, providing the API key via a differently-named env var, or a config file where cloudzero settings keys are misspelled so they default to None.

Common situations: Onboarding CloudZero cost analytics: connection created in the CloudZero dashboard but its ID never copied into proxy config; secrets mounted but env var names differ from expected; staging config promoted to prod without the cloudzero credentials block.

Related errors

• AZURE_SENTINEL_DCR_IMMUTABLE_ID is required. Set it as an en
• AZURE_SENTINEL_ENDPOINT is required. Set it as an environmen
• AZURE_SENTINEL_TENANT_ID or AZURE_TENANT_ID is required. Set
• AZURE_SENTINEL_CLIENT_ID or AZURE_CLIENT_ID is required. Set
• AZURE_SENTINEL_CLIENT_SECRET or AZURE_CLIENT_SECRET is requi

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/19a0cd1129ef7b6a. Report an issue: GitHub.