LLMWhisperer · Rate Limits

Llmwhisperer Rate Limits

LLMWhisperer meters usage by pages processed. The free tier caps usage at 100 pages per day; paid pay-as-you-go usage is billed per 1,000 pages with no documented hard request-per-minute cap published in the public API reference. Extraction is asynchronous, so callers submit to /whisper and poll /whisper-status (or use webhooks) rather than holding a synchronous connection. Specific per-account concurrency and request-rate limits are not reconciled in this artifact.

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

It captures 3 rate-limit definitions, measuring pages, requests, and jobs.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, LLM, Document Extraction, OCR, and Text Extraction.

3 Limits Throttle: 429
AILLMDocument ExtractionOCRText ExtractionRate LimitingQuotasThrottling

Limits

Free Tier Daily Pages account
pages
100
Free plan processes up to 100 pages per day; paid usage removes this cap.
Requests Per Minute (RPM) account
requests
see provider documentation
No public per-minute request cap documented; verify with Unstract.
Concurrency account
jobs
see provider documentation
Concurrent in-flight whisper jobs per account; not publicly documented.

Policies

Asynchronous Processing
Submit to /whisper, then poll /whisper-status or register a webhook; do not hold a synchronous connection.
Polling Backoff
Poll /whisper-status at a reasonable interval and honor Retry-After / 429 responses with exponential backoff.

Sources