Security & Privacy

Interfaze is built with security and privacy as core principles. We understand the importance of protecting your data and ensuring secure AI interactions.

If you require a security review with SOC2 or HIPAA compliance, please contact us at support@interfaze.ai.

Data Privacy

Message Storage

During Closed Beta:

• We store debugging logs for service improvements that doesn't include prompts, responses, or any other sensitive data.
• All data is handled with strict security protocols

From Open Beta Onwards:

• No message storage by default - your conversations are not logged or stored
• Optional observability features will require explicit user consent
• You maintain full control over data retention preferences

Data Processing

• All API requests are processed in real-time
• No persistent storage of your prompts or responses unless explicitly enabled
• Data is encrypted in transit and at rest
• We do not use your data for model training without explicit consent

Zero Data Retention (ZDR)

Zero Data Retention makes a request fully ephemeral. Nothing from the prompt, the response, or any intermediate task output is written to disk or kept after the request completes, including debugging logs.

Turn it on per request with the x-interfaze-zdr header:

x-interfaze-zdr: true

If you use the Interfaze SDK, set zdr: true when creating the client instead and the header is added for you. There is no equivalent option anywhere else, including the native Vercel AI SDK and LangChain integrations, so set the header as a default header on the client so every request carries it.

import { Interfaze } from "interfaze";

const interfaze = new Interfaze({
  apiKey: process.env.INTERFAZE_API_KEY,
  zdr: true, // no prompts, responses, or logs are retained
});

Infrastructure Security

API Security

• HTTPS Only: All API communications are encrypted using TLS 1.3
• API Key Authentication: Secure token-based authentication
• Rate Limiting: Built-in protection against abuse and DDoS attacks
• Request Validation: All inputs are validated and sanitized

Code Execution Security

When using code execution features:

• Sandboxed Environment: All code runs in isolated containers
• Resource Limits: Controlled CPU and memory usage
• Network Isolation: No external network access for security
• Time Limits: Automatic termination of long-running processes
• Safe Execution: Restricted access to system resources

Infrastructure

• Cloud Security: Built on secure, enterprise-grade cloud infrastructure
• Regular Audits: Continuous security monitoring and vulnerability assessments
• Backup & Recovery: Robust disaster recovery and data backup systems
• Compliance: Adherence to industry security standards and best practices

Monitoring

• Real-time usage monitoring
• Automatic rate limit enforcement
• Detailed usage analytics (coming soon)