Lasso Security · Rate Limits

Lasso Security Rate Limits

Lasso Security does not publish specific public rate limits for the Classify / Threat Detection API or the Deputy gateway. Limits are governed by the subscribed plan and enterprise agreement. Clients pass a per-request timeout (default 5000 ms) on classification calls. Standard HTTP throttling (429) is expected on overuse. Specific per-account values are not reconciled in this artifact.

Lasso Security Rate Limits is the machine-readable rate-limit profile for Lasso Security on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 3 rate-limit definitions, measuring requests, milliseconds, and concurrent_requests.

The profile also includes 3 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, LLM, GenAI Security, Guardrails, and MCP.

3 Limits Throttle: 429
AILLMGenAI SecurityGuardrailsMCPRate LimitingQuotasThrottling

Limits

Per-Account Requests account
requests
see provider / contract
Governed by plan and enterprise agreement; not publicly published.
Request Timeout request
milliseconds
5000 default
Client-supplied classification timeout in milliseconds; default 5000 ms.
Concurrency account
concurrent_requests
see provider / contract
Concurrent classification throughput set by plan; not publicly published.

Policies

Plan-Based Limits
Throughput and quotas scale with the subscribed Lasso plan and enterprise terms.
Timeout Handling
Classification requests honor a per-call timeout (default 5000 ms); callers should fail open or closed per their policy.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources