Skip to main content

Models

qomplement provides OCR and Fill models. Choose the right model based on your accuracy needs and use case.

GET /v1/models

Available Models​

qomplement-OCR-v1​

The default model. Fast, cost-effective, and accurate for most documents.

PropertyValue
Model IDqomplement-OCR-v1
TypeStandard OCR + AI structuring
Best forDigital PDFs, clean scans, typed documents
Speed~2-4 seconds per page
Token cost1x (base rate)

Capabilities:

FeatureStatus
Text extractionSupported
Table detectionSupported
Key-value pairsSupported
Schema-guided extractionSupported
Multi-page documentsSupported
Handwriting recognitionLimited
Low-quality scansLimited

qomplement-OCR-XL-v1​

High-precision model for complex or degraded documents. Uses enhanced multi-pass processing for maximum accuracy.

PropertyValue
Model IDqomplement-OCR-XL-v1
TypeEnhanced OCR + multi-pass AI structuring
Best forHandwritten documents, low-quality scans, complex layouts
Speed~5-10 seconds per page
Token cost2x (double base rate)

Capabilities:

FeatureStatus
Text extractionSupported
Table detectionSupported
Key-value pairsSupported
Schema-guided extractionSupported
Multi-page documentsSupported
Handwriting recognitionSupported
Low-quality scansSupported

qomplement-fill-v1​

AI-powered form filling model. Detects PDF form fields and intelligently maps data from source documents, natural language instructions, or explicit mappings.

PropertyValue
Model IDqomplement-fill-v1
TypeAI form field detection + intelligent mapping
Best forPDF form filling, document-to-form automation
Speed~3-8 seconds per form
Token cost1x (base rate)

Capabilities:

FeatureStatus
Form field detectionSupported
Source document extractionSupported
Natural language instructionsSupported
Explicit JSON mappingsSupported
Cross-language field matchingSupported
Confidence scoringSupported
Form flatteningSupported

Three input methods:

MethodDescription
Source documentsUpload source doc(s) — AI extracts data and maps to form fields
InstructionsDescribe what to fill in plain language (e.g., "Fill client name as 'Acme Corp'")
Explicit mappingsProvide JSON {field_name: value} pairs directly

Usage​

Specify the OCR model in extraction or fill endpoints using the model parameter:

curl -X POST https://developer-api.qomplement.com/v1/extract \
-H "Authorization: Bearer sd_your_api_key" \
-F "files=@document.pdf" \
-F "model=qomplement-OCR-XL-v1"

If omitted, the API defaults to qomplement-OCR-v1. The fill endpoint automatically uses qomplement-fill-v1 for field mapping.

Model Versions​

Models are versioned to ensure consistent behavior. The current versions are:

AliasPoints toReleased
qomplement-OCR-v1qomplement-OCR-v1-2025-02February 2025
qomplement-OCR-XL-v1qomplement-OCR-XL-v1-2025-02February 2025
qomplement-fill-v1qomplement-fill-v1-2025-02February 2025

When new versions are released, the alias automatically points to the latest version. Pin a specific version by using the full version ID (e.g., qomplement-OCR-v1-2025-02) if you need deterministic behavior.

Rate Limits​

Rate limits ensure fair access to the API. Your tier determines your limits.

TierMonthly TokensRequests / minMax Pages / requestMax File Size
Free100K101010 MB
Starter500K305025 MB
Growth2.5M6010050 MB
Scale10M120200100 MB

Rate limit headers are included in every response:

X-RateLimit-Limit: 30
X-RateLimit-Remaining: 29
X-RateLimit-Reset: 1709078400

If you exceed your rate limit, the API returns 429 Too Many Requests. See Rate Limiting for details.

Pricing​

Tokens are consumed per page processed. The XL model uses 2x tokens per page.

ModelTokens per page/formApproximate cost
qomplement-OCR-v1~500-1,500Varies by tier
qomplement-OCR-XL-v1~1,000-3,0002x standard
qomplement-fill-v1~500-2,000Varies by tier

Purchase tokens on the Developer Portal:

PackageTokensPricePer 1M tokens
Starter500K$15$30
Growth2.5M$60$24
Scale10M$200$20

Choosing a Model​

ScenarioRecommended Model
Digital PDFs with typed textqomplement-OCR-v1
Clean scans (300+ DPI)qomplement-OCR-v1
Handwritten formsqomplement-OCR-XL-v1
Faded or damaged documentsqomplement-OCR-XL-v1
Mixed typed + handwrittenqomplement-OCR-XL-v1
High-volume batch processingqomplement-OCR-v1
Legal/medical documents requiring accuracyqomplement-OCR-XL-v1
PDF form filling from source documentsqomplement-fill-v1
Form filling with natural language instructionsqomplement-fill-v1
tip

Start with qomplement-OCR-v1 for most use cases. Switch to qomplement-OCR-XL-v1 only if you see accuracy issues with specific document types. You can use the Playground to compare results side by side.