TechPrufer
Get started
Together AI
Together AI logoTogether AI · Feature trail

AI Security and Safety Guardrails

1 post · Jul 2025

What this trail covers

Together AI integrates VirtueGuard, an enterprise-grade AI security and safety model, directly into its platform. This guardrail model provides comprehensive protection against harmful outputs, compliance violations, and reputational damage with an 8ms response time, high F1 score, and low false positive rate across 12 risk categories for text, images, and audio. It offers seamless integration with a single API parameter, enterprise reliability with a 99.9% uptime SLA, automatic scaling, and continuous updates from Virtue AI's research team.

All Together AI trails
  1. VirtueGuard: Enterprise-Grade AI Security and Safety Now on Together AIThis post announces the integration of VirtueGuard, an AI security and safety model, into the Together AI platform. It highlights VirtueGuard's key features: an 8ms response time, an 89% F1 score, a 0.058 false positive rate, and coverage of 12 risk categories across text, images, and audio. The integration allows for seamless deployment via a single API parameter, leveraging Together AI's 99.9% uptime SLA and automatic scaling. The post provides a code example demonstrating how to use the `safety_model` parameter in the Python SDK.