Skip to main content
Retab uses a credit-based pricing system for AI model usage. Different models have different credit costs based on their capabilities and performance characteristics.

​
Credit price

1 Credit = 0.01$

​
Model Pricing

Model FamilyModel VariantCreditsTier
GPT-5nano0.2Micro
mini1.0Small
base3.0Large
Gemini 2.5 / 3.0flash-lite0.2Micro
flash1.0Small
pro3.0Large
Claude 4.0 / 4.5haiku1.0Small
sonnet3.0Large
Retab routerauto-micro0.2Micro
auto-small1.0Small
auto-large3.0Large

​
Extraction API Pricing

This concerns the following endpoints:

​
Pricing Formula

The total cost for an extract request is calculated as: 
credits/page = n_consensus × model_credits

​
Credit Tiers

  • 0.2 credits: Micro models (fastest, most efficient)
  • 0.5 credits: Small models (balanced performance)
  • 3.0 credits: Large models (highest capability)
Where:
  • n_consensus: Number of consensus runs (typically 1-5, depending on your accuracy requirements)
  • model_credits: The credit cost of the specific model you’re using (see table above)

​
Examples

Example 1: Text PDF extraction with GPT-5-Mini
  • Model usage: 1 run × 1.0 credits = 1.0 credits
  • Total: 1.0 credits
Example 2: Scanned document with Gemini-2.5-Pro (3 consensus)
  • Model usage: 3 runs × 3.0 credits = 9.0 credits
  • Total: 6.0 credits
Example 3: JSON extraction with Auto-Micro
  • Model usage: 1 run × 0.2 credits = 0.2 credits
  • Total: 0.2 credits
Example 4: Scanned invoice with Auto-Micro
  • Model usage: 1 run × 0.2 credits = 0.2 credits
  • Total: 0.2 credits

​
Model Selection Guide

Choose Micro models (0.2 credit) when:
  • You need fast, efficient processing
  • Working with simple extraction tasks
  • Cost efficiency is the primary concern
Choose Small models (1.0 credit) when:
  • You need balanced performance and cost
  • Working with moderate complexity tasks
  • Good balance of speed and capability
Choose Large models (3.0 credits) when:
  • You need maximum capability and accuracy
  • Working with complex reasoning tasks
  • Quality is more important than cost

​
Parsing API Pricing

This concerns the following endpoints:

​
Pricing Formula

The total cost for a parse request is calculated as: 
credits/page = model_credits
The Parse API follows the same pricing structure as extraction:
  • 0 credits: For text-based documents
  • model_credits: The credit cost of the specific model you’re using (see table above)

​
Examples

Example 1: PDF parsing with GPT-5-Mini
  • Model usage: 1.0 credits
  • Total: 0.5 credit
Example 2: Scanned document with Gemini-2.5-Flash-Lite
  • Model usage: 0.2 credits
  • Total: 0.2 credit
Example 3: JSON parsing with Auto-Micro
  • Model usage: 0.0 credit
  • Total: 0.0 credit
Example 3: Text parsing with Auto-Small
  • Model usage: 0.0 credit
  • Total: 0.0 credit

​
Edit API Pricing

This concerns the following endpoint: The Edit API allows you to fill PDF forms by inferring form fields and populating them with values based on provided instructions.

​
Pricing Formula

The total cost for an edit request is calculated as: 
credits/page = 3 × model_credits
The Edit API charges 3× the model credits per page because it performs multiple LLM operations:
  1. OCR processing to extract text elements
  2. Form field inference to identify fillable areas
  3. Form filling based on your instructions

​
Examples

Example 1: Single-page form with Gemini-2.5-Pro
  • Model usage: 3 × 3.0 credits = 9.0 credits
  • Total: 9.0 credits
Example 2: 5-page document with Gemini-2.5-Flash
  • Model usage: 3 × 1.0 credits × 5 pages = 15.0 credits
  • Total: 15.0 credits
Example 3: 10-page form with Auto-Large
  • Model usage: 3 × 3.0 credits × 10 pages = 90.0 credits
  • Total: 90.0 credits

​
Use Cases

The Edit API is ideal for:
  • Automatically filling PDF forms with structured data
  • Processing government or legal documents
  • Batch form completion workflows
  • Any scenario requiring programmatic PDF form filling