BerriAI/litellm · error · ValueError

ARIZE_API_KEY not found in environment variables

Error message

ARIZE_API_KEY not found in environment variables

What it means

A cheaper existence-check path for callbacks ('is this integration already configured?') also enforces credentials: for 'arize' it requires ARIZE_API_KEY in the environment before looking for an existing ArizeLogger. Raising here means Arize was referenced (e.g. when pruning/validating configured callbacks) but the API key is missing, so the integration cannot be considered usable.

Source

Thrown at litellm/litellm_core_utils/litellm_logging.py:4554

                    return callback
        elif logging_integration == "opik":
            for callback in _in_memory_loggers:
                if isinstance(callback, OpikLogger):
                    return callback
        elif logging_integration == "langfuse":
            for callback in _in_memory_loggers:
                if isinstance(callback, LangfusePromptManagement):
                    return callback
        elif logging_integration == "otel":
            from litellm.integrations.opentelemetry import OpenTelemetry

            for callback in _in_memory_loggers:
                # Use exact type check to avoid matching ArizePhoenixLogger (subclass)
                if type(callback) is OpenTelemetry:
                    return callback
        elif logging_integration == "arize":
            if "ARIZE_API_KEY" not in os.environ:
                raise ValueError("ARIZE_API_KEY not found in environment variables")
            for callback in _in_memory_loggers:
                if isinstance(callback, ArizeLogger) and callback.callback_name == "arize":
                    return callback
        elif logging_integration == "logfire":
            if "LOGFIRE_TOKEN" not in os.environ:
                raise ValueError("LOGFIRE_TOKEN not found in environment variables")
            from litellm.integrations.opentelemetry import OpenTelemetry

            for callback in _in_memory_loggers:
                # Use exact type check to avoid matching ArizePhoenixLogger (subclass)
                if type(callback) is OpenTelemetry:
                    return callback

        elif logging_integration == "dynamic_rate_limiter":
            from litellm.proxy.hooks.dynamic_rate_limiter import (
                _PROXY_DynamicRateLimitHandler,
            )

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Set ARIZE_API_KEY (and ARIZE_SPACE_KEY plus endpoint vars) in the proxy environment
2. If you meant Arize Phoenix, use the 'arize_phoenix' callback instead of 'arize'
3. Validate required env vars at startup with a preflight check so misconfig fails fast with your own message
4. Remove 'arize' from callbacks where it is not intended

Example fix

# before
litellm_settings:
  callbacks: ["arize"]   # no ARIZE_API_KEY in env

# after
export ARIZE_API_KEY=... ARIZE_SPACE_KEY=... ARIZE_HTTP_ENDPOINT=...
litellm_settings:
  callbacks: ["arize"]

import os
assert os.getenv('ARIZE_API_KEY'), 'ARIZE_API_KEY required when arize is in callbacks'

When it happens

Trigger: Any code path that consults the callback-presence helper for 'arize' — e.g. proxy startup validating litellm_settings.callbacks, or runtime checks before enabling the integration — while ARIZE_API_KEY is unset.

Common situations: ARIZE_SPACE_KEY set but API key forgotten; env var present in one deployment stage but not another; using Arize Phoenix (which needs a different setup) instead of Arize the platform and confusing the two integrations.

Related errors

• No valid endpoint found for Arize, please set 'ARIZE_ENDPOIN
• LOGFIRE_TOKEN not found in environment variables
• LANGTRACE_API_KEY not found in environment variables
• Missing keys={missing_keys} in environment.
• Callback param '{param}' (from {source}) contains an 'os.env

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/a204e8378e677cea. Report an issue: GitHub.