Generalized
Compatible with OpenAI, Anthropic, and more, including self-hosted models.
Private
We don't train on or store any user inputs, and all API traffic follows encryption standards.
Fast
Our highly accurate models are tested for latency, suitable for production environments
complete toolkit
Data redaction
Anonymize and replace sensitive data, including custom entity types
Compliance
Align with data privacy standards and new AI compliance law
Automatic checks
Continuously check and alert on data leakage in model output
Input protection
Screen inputs for prompt injection, malicious code, and jailbreak attempts
Observability
Automated tooling for a high-level view of your data security
Pricing
For individuals
Basic
2k API calls/mo
PII detection and anonymization
Basic prompt protection
Get Started
for teams
Custom
Unlimited usage
Multi-language support
Full prompt protection
24/7 support
PII detection and redaction
Custom alerts, compliance, and observability tooling
Get Started
