EnkryptAI Guardrails

LiteLLM supports EnkryptAI guardrails for content moderation and safety checks on LLM inputs and outputs.

Quick Start

1. Define Guardrails on your LiteLLM config.yaml

Define your guardrails under the guardrails section:

model_list:
  - model_name: gpt-5.6-luna
    litellm_params:
      model: openai/gpt-5.6-luna
      api_key: os.environ/OPENAI_API_KEY

guardrails:
  - guardrail_name: "enkryptai-guard"
    litellm_params:
      guardrail: enkryptai
      mode: "pre_call"
      api_key: os.environ/ENKRYPTAI_API_KEY
      policy_name: "my-policy"  # EnkryptAI policy that defines which detectors run

Supported values for mode

• pre_call - Run before LLM call, on input
• post_call - Run after LLM call, on output
• during_call - Run during LLM call, on input. Same as pre_call but runs in parallel as LLM call

Available Detectors

Detectors are configured in the EnkryptAI policy referenced by policy_name, not in the LiteLLM config. LiteLLM sends only the text and the x-enkrypt-policy header, so a detectors: block under litellm_params has no effect. EnkryptAI policies support these detection types:

• toxicity - Detect toxic language
• nsfw - Detect NSFW (Not Safe For Work) content
• pii - Detect personally identifiable information
  • Entities configurable in the policy: ["pii", "email", "phone", "secrets", "ip_address", "url"]
• injection_attack - Detect prompt injection attempts
• keyword_detector - Detect custom keywords/phrases
• policy_violation - Detect policy violations
• bias - Detect biased content
• sponge_attack - Detect sponge attacks

2. Set Environment Variables

export ENKRYPTAI_API_KEY="your-api-key"

3. Start LiteLLM Gateway

litellm --config config.yaml --detailed_debug

4. Test Request

Langchain, OpenAI SDK Usage Examples

Successful Call

curl -i http://localhost:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
    "model": "gpt-5.6-luna",
    "messages": [
      {"role": "user", "content": "Hello, how can you help me today?"}
    ],
    "guardrails": ["enkryptai-guard"]
  }'

Response: HTTP 200 Success

Content passes all detector checks and is allowed through.

Unsuccessful Call

Expect this to fail if content violates detector policies:

curl -i http://localhost:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
    "model": "gpt-5.6-luna",
    "messages": [
      {"role": "user", "content": "My email is test@example.com and my SSN is 123-45-6789"}
    ],
    "guardrails": ["enkryptai-guard"]
  }'

Expected Response on Failure: HTTP 500 Error

The message is a plain string listing each violation, and its details come from the EnkryptAI response.

{
  "error": {
    "message": "Guardrail failed: 1 violation(s) detected\n\n- PII:\n  PII Detected: {'email': ['test@example.com']}",
    "type": "internal_server_error",
    "param": null,
    "code": "500"
  }
}

Video Walkthrough

Advanced Configuration

Using Custom Policies

You can specify a custom EnkryptAI policy:

guardrails:
  - guardrail_name: "enkryptai-custom"
    litellm_params:
      guardrail: enkryptai
      mode: "pre_call"
      api_key: os.environ/ENKRYPTAI_API_KEY
      policy_name: "my-custom-policy"  # Sent via x-enkrypt-policy header

Detection is controlled entirely by the policy referenced in policy_name; LiteLLM sends only the text and this header to EnkryptAI, so per-detector settings must be configured in the EnkryptAI policy itself. Any detected violation blocks the request.

Input and Output Guardrails

Configure separate guardrails for input and output:

guardrails:
  # Input guardrail
  - guardrail_name: "enkryptai-input"
    litellm_params:
      guardrail: enkryptai
      mode: "pre_call"
      api_key: os.environ/ENKRYPTAI_API_KEY
      policy_name: "my-input-policy"

  # Output guardrail
  - guardrail_name: "enkryptai-output"
    litellm_params:
      guardrail: enkryptai
      mode: "post_call"
      api_key: os.environ/ENKRYPTAI_API_KEY
      policy_name: "my-output-policy"

Configuration Options

Parameter	Type	Description	Default
api_key	string	EnkryptAI API key	ENKRYPTAI_API_KEY env var
api_base	string	EnkryptAI API base URL	https://api.enkryptai.com
policy_name	string	Custom policy name (sent via x-enkrypt-policy header)	None
mode	string	When to run: pre_call, post_call, or during_call	Required

Observability

EnkryptAI guardrail logs include:

• guardrail_status: success, guardrail_intervened, or guardrail_failed_to_respond
• guardrail_provider: enkryptai
• guardrail_json_response: Full API response with detection details
• duration: Time taken for guardrail check
• start_time and end_time: Timestamps

These logs are available through your configured LiteLLM logging callbacks.

Error Handling

The guardrail handles errors gracefully:

• API Failures: Logs error and raises exception
• Rate Limits (429): Logs error and raises exception
• Invalid Configuration: Raises ValueError on initialization
• Violations Detected: Raises an exception and blocks the request

Support

For more information about EnkryptAI:

• Documentation: https://docs.enkryptai.com
• Website: https://enkryptai.com