One End Point
All Document Types
We're on a mission to revolutionize document processing by providing a single endpoint for a variety of document types to extract structured text, and rich metadata. Scalable to enterprise workloads.
curl -X POST "https://api.omnitext.io/v1/extract/text" \
-H "Authorization: Bearer your_api_key" \
-F "file=@document.docx"
# Response
{
"text": "Extracted text content...",
"metadata": {
"pages": 10,
"word_count": 1250
}
}const formData = new FormData();
formData.append('file', fileInput.files[0]);
const response = await fetch('https://api.omnitext.ai/v1/extract/text', {
method: 'POST',
headers: {
'x-api-key': 'your_api_key'
},
body: formData
});
const result = await response.json();
console.log(result.text);import requests
url = "https://api.omnitext.ai/v1/extract/text"
headers = {"x-api-key": "your_api_key"}
files = {"file": open("document.docx", "rb")}
response = requests.post(url, headers=headers, files=files)
result = response.json()
print(result['text'])
print(result['metadata'])Everything you need to process documents
From simple and structured text extraction to AI-powered embeddings.
Universal Document Parsing
Extract text from any document format with industry-leading accuracy
- PDF, DOCX, PPTX, XLSX support
- OCR for scanned documents
- Maintains formatting structure
- Batch processing capabilities (coming soon)
Multiple Output Formats
Get your data in the format you need for your application
- Plain text extraction
- Structured HTML output
- Clean Markdown conversion
- Vector Embeddings
Enterprise-Scale Throughput
Global infrastructure designed to handle massive workloads with predictable performance
- Combined 650K+ docs/hr or 2.5M+ PDF pages/hr
- Scalable for any workload size
- 40 regions worldwide deployment
- Higher processing available - contact sales team
Developer Experience
Built by developers, for developers with modern API design
- RESTful API design
- Detailed documentation
- Simple authentication
- Comprehensive SDKs (Coming Soon)
Get started in minutes
From signup to your first successful API call in under 5 minutes. No complex setup required.
1. Register/Sign in
Create your free account to get started. No credit card required for the free tier - get 1,000 documents per month to test our API.
2. Create API Key
Once logged in, navigate to your dashboard and generate your API key. Keep it secure - this key authenticates all your API requests.
3. Send API Request
Use your API key to make your first document extraction request. Choose from multiple programming languages or use cURL for quick testing.
4. Get Your Response
Receive structured data with extracted text, metadata, and processing information. The response includes confidence scores and detailed document analysis.
Simple, transparent pricing
Choose the perfect plan for your document processing needs. Scale up or down as your business grows.
- 1,000 requests per day
- 100 credits per month
- 30 days data retention
- SDK integration (coming soon)
- Encrypted file transfer
- Email support (72h response)
- Basic1 credit
- Basic (OCR)3 credits (per 20 pages)
- Advanced Document Analysis5 credits
- Advanced (OCR)12 credits (per 20 pages)
- EmbeddingsText Parser Cost + 1 Credit
Complete Documentation
Everything you need to integrate and use our text processing API effectively.
API Reference
Comprehensive API documentation with detailed endpoint specs, parameters, and response formats.
- Interactive examples
- Response schemas
- Error handling
- Authentication guide
Guides
Step-by-step tutorials for popular programming languages and frameworks.
- Python & JavaScript
- cURL examples
- Best practices
SDKs & Libraries
Coming Soon for the following languages
- Python
- Typescript/Javascript
- Golang
Ready to Transform Your
Document Processing?
Join thousands of developers already using our API to extract, convert, and process documents at scale. Start building today with our generous free tier.
No credit card required • 100 free credits Per Month • PAYG Api Keys
