In summary
- Fastly has launched three new capabilities - AI Runtime Control, AI Firewall, and expanded API Security - to give organisations real-time visibility and control across AI systems, models and agents.
- AI Runtime Control routes model calls through a single endpoint with virtual keys, token spend visibility, rate limiting, budget controls and failover, while AI Firewall blocks prompt injection and other LLM-based attacks in the request path.
- The updated API Security capability enforces API contracts across agentic, agent-assisted and conventional traffic.
Fastly has launched three new capabilities - AI Runtime Control, AI Firewall, and expanded API Security - designed to give organisations real-time visibility and control across AI systems, models and agents.
The capabilities are aimed at organisations running AI in production that need to govern model access, protect AI applications and control how AI agents interact with enterprise APIs.
AI Runtime Control routes model calls through a single endpoint across public and self-hosted model providers, with virtual keys to protect underlying provider credentials. It includes real-time token spend visibility, rate limiting, budget controls and failover - letting organisations enforce policy centrally while retaining model choice.
AI Firewall targets large language model-based attacks including prompt injection, evaluating prompts directly in the request path and blocking malicious activity before it reaches the targeted model.
The updated API Security capability enforces API contracts across agentic, agent-assisted and conventional traffic, allowing organisations to observe or block non-conforming requests on a service-by-service basis.
"Fastly is extending the real-time control customers already trust for content delivery and software security to the models, applications, and agents shaping this new era of distributed systems," said Kelly Shortridge, chief product officer at Fastly.
"Organisations deserve the freedom to move fast with AI while staying safe, achieving innovation at scale without trading off resilience.”
The new capabilities sit alongside existing platform features including Bot Management, ContentGuard, DDoS Protection, API Discovery and Next-Gen WAF. Fastly said its network runs at 622 Tbps of global edge capacity, as of 30 June 2026, handling more than five trillion requests daily as of 31 March 2026.




