Skip to main content
This guide covers the most common issues you might encounter when integrating with PromptGuard and provides step-by-step solutions.

Authentication Issues

Invalid API Key Error

Problem: Getting 401 Unauthorized errors when making requests. Symptoms:
Solutions:
Check that your API key is properly set:
If you’re getting authentication errors, verify that:
  • Your API key is correctly copied (no extra spaces or newlines)
  • The key is from the correct project
  • The key hasn’t been deleted or deactivated
Ensure your API key is properly set:
Check if your API key is active in the dashboard:
  1. Login to app.promptguard.co
  2. Navigate to Connect → API Keys
  3. Verify the key exists and is not revoked
  4. Check your subscription is active and within request limits

Subscription or Quota Errors

Problem: Request blocked due to subscription tier or monthly limit. Symptoms:
  • 429 Too Many Requests with monthly_quota_exceeded in the response body when the month’s usage credit is spent (Free hard limit), spending_limit_exceeded when usage past the credit has reached its spending cap, or subscription_inactive when the subscription has lapsed.
  • Access to certain features (e.g. custom policies, ML detection) requires Developer or higher.
Solutions:
  1. Check usage and limits in the dashboard (Billing / Usage)
  2. Upgrade your plan if you need higher limits or more features
  3. Ensure the API key belongs to a user with an active subscription

Connection Issues

Network Timeout Errors

Problem: Requests timing out or failing to connect. Symptoms:
  • Connection timeout errors
  • Network unreachable errors
  • DNS resolution failures
Solutions:
Test basic connectivity to PromptGuard:
Increase timeout values in your client:
Ensure your network allows outbound HTTPS connections:
  • Whitelist api.promptguard.co in firewall
  • Configure proxy settings if required
  • Check corporate network restrictions

Security Policy Issues

Unexpected Request Blocks

Problem: Legitimate requests being blocked by security policies. Symptoms:
Solutions:
  1. Open app.promptguard.co
  2. Navigate to Security > Events
  3. Find the blocked request
  4. Review the detection reason
  5. Determine if it’s a false positive
If you’re getting too many false positives:
  1. Go to Projects > [Your Project] > Guardrails
  2. Switch to a more permissive preset (e.g., from RAG System to Default)
  3. Test your application
  4. Gradually increase security as needed
For legitimate patterns being blocked:
  1. Navigate to Security > Custom Rules
  2. Create an “Allow” rule for the specific pattern
  3. Test to ensure the rule works correctly

High False Positive Rate

Problem: Too many legitimate requests being flagged as threats. Solutions:
  1. Start with Default preset during development
  2. Gradually increase security in staging
  3. Monitor false positive rate in dashboard
  4. Create custom whitelist rules for your use cases
  5. Contact support for policy tuning assistance

Detection issues

Each of these is decided by the project’s preset and guardrails, which you change in the dashboard:
  • False positives. Move the project to a more permissive strictness level, set a lower level on the one guardrail that fires (per-guardrail configuration), or add an allow rule for the legitimate pattern (custom rules).
  • A threat that was not caught. Use a stricter level on that guardrail, or add a custom rule for the pattern your application sees. Some attacks no detector catches reliably: Detection limits lists them and the controls that do not depend on detection.
  • Slow scans. Which detectors are slow and why, and how to keep the guard call fast: Latency budgets.

Performance Issues

High Latency

Problem: Requests taking longer than expected. Expected Performance:
  • PromptGuard overhead: the deterministic fast path runs in under 10 ms (measured). By default a request it finds clean continues to the ML classifiers, which is materially slower; see latency budgets for the measured figures and how to measure your own traffic
  • Total latency: OpenAI/Anthropic latency + the overhead above, which depends on your escalation rate rather than on a detection-mode constant
Troubleshooting:
Cache responses for identical requests:

Rate Limiting Issues

Too Many Requests Error

Problem: Hitting rate limits. Symptoms:
Solutions:
Monitor rate limit status:
Use multiple API keys to increase limits:

Model and Provider Issues

Model Not Found Error

Problem: Specified model is not available. Symptoms:
Solutions:
Verify the model name is correct:
Which model ids go to which provider is on each provider’s page under Integrations. A model id no provider claims is refused rather than guessed.
Ensure your provider API keys are configured:
  1. Go to app.promptguard.co
  2. Navigate to Settings > Provider Keys
  3. Add your OpenAI and/or Anthropic API keys
  4. Test the connection

Provider API Key Issues

Problem: Underlying provider (OpenAI/Anthropic) API key is invalid. Solutions:
  1. Update provider keys in PromptGuard dashboard
  2. Verify keys are active in provider’s dashboard
  3. Check subscription tier for the models/features you’re using
  4. Ensure sufficient credits in provider account

Streaming Issues

Streaming Responses Cut Off

Problem: Streaming responses stop unexpectedly. Solutions:
For serverless deployments:

Integration-Specific Issues

Next.js API Routes

Problem: Issues with Next.js API integration. Common Solutions:
Ensure proper environment variable setup:
Configure CORS for frontend requests:

Getting Help

Diagnostic Information

When contacting support, include:

Support Channels

Email Support

Technical support for integration issues

System Health

Check API status in real-time

Integration Guides

Complete integration guides and examples

Examples

See working code examples

Debug Mode

Enable debug logging for detailed troubleshooting:
Most issues can be resolved by following these troubleshooting steps. If you continue to experience problems, don’t hesitate to reach out to our support team with the diagnostic information above.
Last modified on November 13, 2026