PromptLayer · Rate Limits

Promptlayer Rate Limits

PromptLayer governs usage primarily through plan-based monthly request (transaction) volumes rather than publicly documented per-minute request ceilings. Included monthly request volumes vary by plan (2.5k Free/Pro, 100k Team, custom Enterprise) with pay-as-you-go overage above the included amount. Evaluation cell executions and dataset sizes are also capped per plan. Specific per-second / per-minute API throttling thresholds are not published and are not reconciled in this artifact.

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

It captures 6 rate-limit definitions, measuring requests and executions.

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

Tagged areas include AI, LLM, Prompt Engineering, Prompt Management, and Observability.

6 Limits Throttle: 429
AILLMPrompt EngineeringPrompt ManagementObservabilityRate LimitingQuotasThrottling

Limits

Monthly Requests (Free) account
requests
2500
Included monthly logged requests on the Free plan; no overage.
Monthly Requests (Pro) account
requests
2500
Included monthly logged requests on Pro; overage billed at $0.003 per request.
Monthly Requests (Team) account
requests
100000
Included monthly logged requests on Team; overage billed at $0.002 per request.
Monthly Requests (Enterprise) account
requests
custom
Custom request volumes negotiated per Enterprise agreement.
Eval Cell Executions account
executions
see provider documentation
Capped per plan (250/mo Free, 7.5k+/mo Team); varies by tier.
Per-Endpoint API Throttling account
requests
see provider documentation
Per-second/per-minute throttling thresholds are not publicly documented.

Policies

Plan-Based Quotas
Usage allowances (requests, eval executions, dataset size) increase as accounts move from Free to Pro to Team to Enterprise.
Pay-as-you-go Overage
Requests beyond the included monthly volume are billed per request on paid plans.
Backoff Strategy
Clients should implement exponential backoff with jitter on 429 responses and honor Retry-After when present.

Sources