Lakera · Rate Limits
Lakera Ai Rate Limits
API Commons Rate Limits 0.1 representation of Lakera Guard SaaS rate-limit policies. Specific numerical limits are not publicly published; figures below represent publicly-documented design targets.
Lakera Ai Rate Limits is the machine-readable rate-limit profile for Lakera on the APIs.io network, conforming to the API Commons Rate Limits specification.
The profile also includes 2 backoff/retry policies defined.
Tagged areas include AI Security, Artificial Intelligence, Generative AI, LLM Security, and Prompt Injection.
0 Limits
AI SecurityArtificial IntelligenceGenerative AILLM SecurityPrompt InjectionAI GuardrailsAI Red TeamingData Loss PreventionContent ModerationCheck Point
Policies
Lakera Guard SaaS Design Target
Lakera markets Guard as scaling to "hundreds of prompts per second" with sub-50ms p95 latency. Hard per-key limits and burst behavior are negotiated by plan and are not publicly published.
Guard Results Endpoint (Analysis)
The /v2/guard/results endpoint is intended for offline analysis and threshold tuning, not for runtime decisions. Lakera applies tighter limits to discourage runtime use.