LLMWhisperer · FinOps Profile

Llmwhisperer Finops

FinOps view of LLMWhisperer spend. LLMWhisperer bills usage-based per-page rates that vary by extraction mode (native_text, low_cost, high_quality, form/table), with a free allowance of 100 pages per day. Cost is driven by the number of pages processed and the mode selected, so the primary optimization levers are choosing the lowest sufficient mode and limiting pages_to_extract to only the pages needed.

Llmwhisperer Finops is the FinOps profile for LLMWhisperer on the APIs.io network, aligned with the FinOps Foundation Framework.

It defines 5 billable meters, billed in USD, on a monthly cycle, and pricing category usage-based.

The profile maps 8 FOCUS columns for cost-allocation reporting.

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

Category: AI and Machine Learning Pricing: Usage-Based Billing: Monthly FOCUS v1.3
AILLMDocument ExtractionOCRText ExtractionFinOpsCost ManagementFOCUS

Framework Alignment

Framework
FinOps Foundation Framework
Data Spec
FOCUS v1.3

Charge Categories

UsageAdjustment

FOCUS Columns

BillingCurrency
USD
ChargeCategory
Usage
InvoiceIssuerName
Unstract
PricingCategory
Usage-Based
ProviderName
Unstract
PublisherName
Unstract
ServiceCategory
AI and Machine Learning
ServiceName
LLMWhisperer

Meters

pages_native_text
Unit: pages
Pages processed in native_text mode, billed per 1,000 pages.
pages_low_cost
Unit: pages
Pages processed in low_cost mode, billed per 1,000 pages.
pages_high_quality
Unit: pages
Pages processed in high_quality mode, billed per 1,000 pages.
pages_high_quality_form
Unit: pages
Pages processed in high_quality with form/table elements, billed per 1,000 pages (highest rate).
free_pages
Unit: pages
Pages consumed under the free 100-pages/day allowance.

Sources