Chunkr · Rate Limits

Chunkr Ai Rate Limits

Chunkr Cloud meters usage primarily through monthly credit and included-page allowances per subscription tier rather than per-second request quotas; exhausting the allowance moves a workload into per-page overage. Because parse and extract are asynchronous task jobs that are submitted and then polled, concurrency and queue limits apply per account and rise with tier. Specific per-account request, concurrency, and queue values are not published and are not reconciled in this artifact.

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

It captures 4 rate-limit definitions, measuring pages, credits, tasks, and requests.

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

Tagged areas include Document Parsing, OCR, Chunking, RAG, and Document Intelligence.

4 Limits Throttle: 429
Document ParsingOCRChunkingRAGDocument IntelligenceRate LimitingQuotasThrottling

Limits

Monthly Page Allowance account
pages
see plan tier
Included pages per month per subscription tier; overage billed per page.
Monthly Credit Allowance account
credits
see plan tier
Credits consumed per processed page (roughly one credit per page).
Concurrent Tasks account
tasks
see provider documentation
Number of parse/extract tasks that can process concurrently; varies by tier.
Task Submission Rate account
requests
see provider documentation
Submission throttling applies to POST /tasks/parse and /tasks/extract.

Policies

Tiered Allowances
Page and credit allowances and concurrency raise as accounts move from Free to Starter, Dev, Growth, and Enterprise.
Polling Discipline
Tasks are asynchronous; clients should poll GET /tasks/{task_id} with backoff rather than tight loops.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources