BerriAI/litellm · critical · ValueError

EnkryptAI API key is required. Set ENKRYPTAI_API_KEY environ

Error message

EnkryptAI API key is required. Set ENKRYPTAI_API_KEY environment variable or pass api_key parameter.

What it means

ValueError raised in EnkryptAIGuardrail.__init__ when both the api_key parameter and the ENKRYPTAI_API_KEY environment variable are empty. The guardrail is constructed when the proxy loads its guardrails-config, so the error aborts guardrail initialization (typically proxy startup) before any moderation call is made.

Source

Thrown at litellm/proxy/guardrails/guardrail_hooks/enkryptai/enkryptai.py:59

GUARDRAIL_NAME: Final = "enkryptai"


class EnkryptAIGuardrails(CustomGuardrail):
    def __init__(
        self,
        guardrail_name: str = "litellm_test",
        api_key: str | None = None,
        api_base: str | None = None,
        policy_name: str | None = None,
        **kwargs,
    ):
        self.async_handler = get_async_httpx_client(llm_provider=httpxSpecialProvider.GuardrailCallback)

        # Set API configuration
        self.api_key = api_key or os.getenv("ENKRYPTAI_API_KEY")
        if not self.api_key:
            raise ValueError(
                "EnkryptAI API key is required. Set ENKRYPTAI_API_KEY environment variable or pass api_key parameter."
            )

        self.api_base = api_base or os.getenv("ENKRYPTAI_API_BASE", "https://api.enkryptai.com")
        self.api_url = f"{self.api_base}/guardrails/policy/detect"

        # Policy name can be passed as parameter or use guardrail_name
        self.policy_name = policy_name
        self.guardrail_name = guardrail_name
        self.guardrail_provider = "enkryptai"

        # store kwargs as optional_params
        self.optional_params = kwargs

        # Set supported event hooks
        kwargs.setdefault("supported_event_hooks", list(self.get_supported_event_hooks()))

        super().__init__(guardrail_name=guardrail_name, **kwargs)

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set ENKRYPTAI_API_KEY in the environment the proxy process actually runs in.
2. Or pass api_key: os.environ/ENKRYPTAI_API_KEY in the guardrail's litellm_params.
3. Restart the proxy — the check runs once at construction.
4. Confirm the variable name spelling with printenv | grep ENKRYPT in the same shell/service context.

Example fix

# before
litellm_params:
  guardrail: enkryptai
  policy_name: my-policy

# after
litellm_params:
  guardrail: enkryptai
  policy_name: my-policy
  api_key: os.environ/ENKRYPTAI_API_KEY

import os

if not (os.getenv('ENKRYPTAI_API_KEY') or cfg.litellm_params.get('api_key')):
    raise SystemExit('ENKRYPTAI_API_KEY not set — refusing to start with enkryptai guardrail')

try:
    guardrail = EnkryptAIGuardrail(litellm_params=cfg)
except ValueError as e:
    if 'ENKRYPTAI_API_KEY' in str(e):
        logger.error('deploy misconfigured: %s', e)
        raise
    raise

When it happens

Trigger: An enkryptai guardrail entry with no api_key in litellm_params while ENKRYPTAI_API_KEY is unset in the proxy's environment; deployments where the secret exists locally but was not injected into the container/service.

Common situations: Missing entry in docker-compose environment or Kubernetes secret; env var named differently (ENKRYPT_AI_API_KEY); .env file not loaded by the service runner; CI runs without secrets.

Understand the failure class

Background: "environment variable is not set" and "Missing keys in environment" errors: what missing required env var messages mean and how to fix them — this error's family across 28 libraries.

Related errors

• DynamoAI API key is required. Set DYNAMOAI_API_KEY environme
• api_base is required for Generic Guardrail API. Set GENERIC_
• Gray Swan guardrail requires a guardrail_name
• Gray Swan API key missing. Set `GRAYSWAN_API_KEY` or pass `a
• llm_as_a_judge guardrail requires a guardrail_name

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/fc34943835babf16. Report an issue: GitHub.