LDX hubLDX hub
  • Pricing
  • Documentation
  • API Reference
Getting Started
    IntroductionCredits & PricingMCP Setup
powered by Zuplo
Getting Started

Credits & Pricing

LDX hub uses a credit-based billing system. Credits are consumed each time you process data through the API. The number of credits consumed depends on the service, model or product you choose, and the volume of data processed.


How Credits Work

One credit costs $0.0001.

Credit consumption varies by service type:

StructFlow / RefineLoop — billed per character:

Code
credits = (input_characters × input_rate + output_characters × output_rate + vector_bytes × vector_bytes_rate) / 1000

RenderOCR / CastDoc — billed per page:

Code
credits = input_pages × rate

AnalyzeDoc — billed per page, plus generated output characters. PDF inputs additionally incur input character charges:

Code
credits = input_pages × page_rate + output_characters × output_rate / 1000 + input_characters × input_rate / 1000
  • page_rate depends on the model and its resolution variant (@high / @medium / @low) and is applied directly per page.
  • Image inputs (JPEG, PNG) count as 1 page and carry no input characters — only the page and output terms apply.
  • PDF inputs are billed per page plus the extracted input characters. For Google Gemini and Amazon Nova models the input character rate is 0 (these models normalize text into the page budget), so PDF is effectively billed per page only.

For example, using Google Gemini 3.5 Flash (google/gemini-3.5-flash) with 10,000 input characters and 10,000 output characters:

Code
credits = (10,000 × 45 + 10,000 × 270) / 1000 = 3,150

So 10,000 input characters and 10,000 output characters consumes 3,150 credits.

Note for RefineLoop: Actual credit consumption is significantly higher than the formula above suggests. RefineLoop processes each segment multiple times (up to 6 iterations by default), and each iteration includes both source and target text. As a result, the actual input_characters charged can be several times the length of the original XLIFF content.


Model & Product Rates

StructFlow

ModelInput RateOutput RateVector Bytes Rate
openai/gpt-5.6-sol1509003
openai/gpt-5.6-terra754503
openai/gpt-5.6-luna301803
openai/gpt-5.51509003
openai/gpt-5.4754503
openai/gpt-5.4-mini231353
azure/gpt-5.6-sol18010804
azure/gpt-5.6-terra905404
azure/gpt-5.6-luna362164
azure/gpt-5.4905404
azure/gpt-5.4-mini271624
google/gemini-3.5-flash452704
google/gemini-3.1-pro-preview603604
google/gemini-3-flash-preview15904
anthropic/claude-fable-53001500—
anthropic/claude-sonnet-590450—
anthropic/claude-opus-4-8150750—
anthropic/claude-opus-4-7150750—
anthropic/claude-sonnet-4-690450—
bedrock/global.amazon.nova-2-lite-v1:0975—
xai/grok-4.560180—
xai/grok-4.33875—
xai/grok-4.20-non-reasoning3875—

AnalyzeDoc

Billed per page based on the model's resolution variant, plus output characters. PDF inputs also incur input character charges (zero-rated for Gemini and Nova).

ModelPage RateOutput RatePDF Input Rate
openai/gpt-5.6-sol@high602900150
openai/gpt-5.6-sol@low63900150
openai/gpt-5.6-terra@high30145075
openai/gpt-5.6-terra@low3245075
openai/gpt-5.6-luna@high12118030
openai/gpt-5.6-luna@low1318030
openai/gpt-5.5@high602900150
openai/gpt-5.5@low63900150
openai/gpt-5.4@high30145075
openai/gpt-5.4-mini@high9113523
azure/gpt-5.6-sol@high3341080180
azure/gpt-5.6-sol@low761080180
azure/gpt-5.6-terra@high16754090
azure/gpt-5.6-terra@low3854090
azure/gpt-5.6-luna@high6721636
azure/gpt-5.6-luna@low1621636
azure/gpt-5.4@high16754090
azure/gpt-5.4@low3854090
azure/gpt-5.4-mini@high5116227
azure/gpt-5.4-mini@low1216227
google/gemini-3.5-flash@high662700
google/gemini-3.5-flash@medium322700
google/gemini-3.5-flash@low162700
anthropic/claude-fable-519091500300
anthropic/claude-sonnet-557345090
anthropic/claude-opus-4-8955750150
bedrock/global.amazon.nova-2-lite-v1:04750

Page Rate is applied directly per page. Output Rate and PDF Input Rate are divided by 1,000 (per character). Higher resolution variants read dense layouts and fine print more accurately at a higher per-page cost.

RefineLoop

ModelInput RateOutput RateVector Bytes Rate
openai/gpt-5.6-sol1509003
openai/gpt-5.6-terra754503
openai/gpt-5.6-luna301803
openai/gpt-5.51509003
openai/gpt-5.4754503
openai/gpt-5.4-mini231353
azure/gpt-5.6-sol18010804
azure/gpt-5.6-terra905404
azure/gpt-5.6-luna362164
azure/gpt-5.4905404
azure/gpt-5.4-mini271624
google/gemini-3.5-flash452704
google/gemini-3.1-pro-preview603604
google/gemini-3-flash-preview15904
anthropic/claude-fable-53001500—
anthropic/claude-sonnet-590450—
anthropic/claude-opus-4-8150750—
anthropic/claude-opus-4-7150750—
anthropic/claude-sonnet-4-690450—
bedrock/global.amazon.nova-2-lite-v1:0975—
xai/grok-4.560180—
xai/grok-4.33875—
xai/grok-4.20-non-reasoning3875—

Rates are divided by 1,000 to calculate actual credit consumption per character.

Vector Bytes Rate applies when using external reference files. Consumption is calculated per byte of the reference file.

RenderOCR

ProductPage Rate
ki/ocr320

Rate is applied directly per page (not divided by 1,000).

CastDoc

ProductPage Rate
ki/cast320

Rate is applied directly per page (not divided by 1,000).


Capacity by Plan

Example: StructFlow with Google Gemini 3.5 Flash

The following estimates are based on Google Gemini 3.5 Flash (google/gemini-3.5-flash) with a 1:1 input/output ratio. Actual consumption varies depending on model choice, input/output ratio, and content length.

PlanCreditsInput Characters (est.)
Free25,000~79,000
Starter150,000~476,000
Standard520,000~1,650,000
Pro1,700,000~5,396,000

Example: AnalyzeDoc with Google Gemini 3.5 Flash @high

The following estimates are based on Google Gemini 3.5 Flash @high (google/gemini-3.5-flash@high), assuming a single-page document that produces ~500 characters of extracted JSON. Each document costs 66 (page) + 500 × 270 / 1,000 (output) = 201 credits. Actual consumption varies with document size, model, resolution variant, and output length.

PlanCreditsDocuments (est.)
Free25,000~124
Starter150,000~746
Standard520,000~2,587
Pro1,700,000~8,457

Example: RenderOCR with KI OCR

PlanCreditsPages (est.)
Free25,000~78
Starter150,000~468
Standard520,000~1,625
Pro1,700,000~5,312

Example: CastDoc with KI Cast

PlanCreditsPages (est.)
Free25,000~78
Starter150,000~468
Standard520,000~1,625
Pro1,700,000~5,312

Notes

  • Credits are reset monthly at the start of each billing period.
  • Unused credits do not carry over to the next period.
  • On paid plans, additional usage beyond the included credits is billed at $0.0001 per credit.
Last modified on July 10, 2026
IntroductionMCP Setup
On this page
  • How Credits Work
  • Model & Product Rates
    • StructFlow
    • AnalyzeDoc
    • RefineLoop
    • RenderOCR
    • CastDoc
  • Capacity by Plan
    • Example: StructFlow with Google Gemini 3.5 Flash
    • Example: AnalyzeDoc with Google Gemini 3.5 Flash @high
    • Example: RenderOCR with KI OCR
    • Example: CastDoc with KI Cast
  • Notes