AI-powered privacy protection and data anonymization
Text Anonymization API
AI-powered API for anonymizing sensitive information in text, files, and web content. The Text Anonymization API provides a secure and efficient way to identify and redact sensitive information from various content sources.
Using advanced AI technology, the API can detect and anonymize a wide range of entity types including personal information, dates, locations, financial data, and more with enterprise-grade security.
Free tier included, no credit card required. One key works across all 49 APIs.
- Entity Types
- 20+
- Accuracy Rate
- 97.8%
- Compliance
- 100%
Key features
- Anonymize plain text with customizable entity redaction
- Process content from uploaded files (PDF, TXT, HTML)
- Anonymize content from web URLs
- Flexible input/output formats with JSON responses
- Secure API with enterprise-grade authentication
Built for
- Privacy compliance (GDPR, CCPA, HIPAA)
- Document sanitization for legal teams
- Customer data protection systems
- Research data anonymization
- Healthcare records processing
- Financial document redaction
- HR document protection
- Data sharing compliance
Try it
Build the request for your data
Edit the parameters below and see the exact curl command and JSON response you will get. No key required to preview.
POST /parser/v1/text HTTP/1.1
Host: api.apicodex.io
Host: api.apicodex.io
Content-Type: application/json
X-Api-Key: YOUR_API_KEY
"text": "John Smith works at Acme Inc. Email: john@acme.com",
"entities": ["PERSON", "EMAIL", "ORG"]
{
"success": true,
"anonymized_text": "[PERSON] works at [ORG]. Email: [EMAIL]",
"entities_found": [
{ "type": "PERSON", "value": "John Smith", "start": 0, "end": 10 },
{ "type": "ORG", "value": "Acme Inc", "start": 20, "end": 28 },
{ "type": "EMAIL", "value": "john@acme.com", "start": 37, "end": 50 }
]
}Documentation
Text Anonymization API Documentation
Learn how to use the Text Anonymization API to protect sensitive information in your content. The API supports text input, file uploads, and URL-based content processing.
Base URL
https://api.apicodex.io/parserAuthentication
Authenticate every request with your API key: send it in an X-Api-Key header, or pass it as an ?apikey= query parameter.
{
"X-Api-Key": "YOUR_API_KEY"
}Request and response
Illustrative values. Confirm current endpoint behavior, quotas, and data freshness in the API documentation before production use.
POST /v1/text HTTP/1.1
Host: api.apicodex.io
Content-Type: application/json
X-Api-Key: YOUR_API_KEY
{
"text": "John Smith works at Acme Inc. Email: john@acme.com",
"entities": ["PERSON", "EMAIL", "ORG"]
}{
"success": true,
"anonymized_text": "[PERSON] works at [ORG]. Email: [EMAIL]",
"entities_found": [
{ "type": "PERSON", "value": "John Smith", "start": 0, "end": 10 },
{ "type": "ORG", "value": "Acme Inc", "start": 20, "end": 28 },
{ "type": "EMAIL", "value": "john@acme.com", "start": 37, "end": 50 }
]
}Code examples
const axios = require('axios');
const options = {
method: 'POST',
url: 'https://api.apicodex.io/parser/v1/text',
headers: {
'content-type': 'application/json',
'X-Api-Key': 'YOUR_API_KEY'
},
data: {
text: 'John Smith works at Acme Inc. Contact: john@acme.com',
entities: ['PERSON', 'EMAIL', 'ORG']
}
};
try {
const response = await axios.request(options);
console.log(response.data);
} catch (error) {
console.error(error);
}Entity Types
The API supports the following types of analysis:
PERSON Names and personal identifiersEMAIL Email addressesPHONE Phone numbersADDRESS Physical addressesDATE Dates and timestampsLOCATION Place names and coordinatesFINANCIAL Credit cards, bank accountsID ID numbers, passports, SSNCUSTOM User-defined patternsPricing
Text Anonymization API Pricing
One key, one subscription, all 49 APIs. Start free and upgrade when you grow. No minimums, no lock-in.
This API costs 25 credits per request. Credits are shared across every API on your plan.
Estimate your monthly cost
Drag the slider to match your expected request volume. We will recommend the cheapest plan that covers it.
Recommended plan
Pro
$99.99 /month
Free
- All 49 APIs included
- No credit card required
- Full documentation and examples
Starter
Popular- All 49 APIs included
- Email support
- Usage dashboard and analytics
Pro
- All 49 APIs included
- Priority support
- Up to 5 API keys
Need a different plan?
Tell us about your API, volume, or support requirements.
Coming soon · MCP
Use the Text Anonymization API from your AI agent
The API Codex MCP server will expose this API, and the other 39, to Claude, Cursor and any MCP client as tools. Same key, same credits, one config entry.
FAQ
Frequently asked questions
The API can detect and anonymize a wide range of sensitive information including personal identifiers (names, emails, phone numbers), financial data (credit card numbers, bank accounts), locations (addresses, coordinates), dates, and custom entity types. The AI model is trained to recognize patterns and context to ensure comprehensive anonymization.
API Codex uses one credit-based subscription across all 40 APIs. The Free plan includes 1,000 credits per month, Starter ($29.99/month) includes 50,000 and Pro ($99.99/month) includes 250,000. Each anonymization request costs 25 credits, so that covers roughly 40 requests per month on Free, 2,000 on Starter and 10,000 on Pro. Only successful (2xx) responses consume credits. If you need higher limits, contact us for a custom plan.
Yes, the Text Anonymization API is designed to help organizations achieve GDPR, CCPA, and HIPAA compliance. The API processes data securely without storing sensitive information, and automatically redacts personal data to meet privacy regulations. All processing is done in memory with encrypted connections, and no source content or PII is retained after anonymization. This makes it ideal for organizations that need to share data while maintaining regulatory compliance.
Our AI uses advanced natural language processing to understand context and distinguish between PII and normal text. For example, 'John Smith' in a signature block is detected as a person's name, while 'John Smith Avenue' is recognized as a street address component. The model analyzes surrounding text, capitalization patterns, and linguistic structure to accurately identify entities based on their contextual usage rather than simple pattern matching.
Yes, the API supports custom entity detection beyond the standard PII categories. You can define custom patterns and entity types specific to your industry or use case. For example, you might want to anonymize employee IDs, project codes, internal department names, or proprietary terminology. Custom entity support is available on Pro plans and above, allowing you to tailor the anonymization process to your organization's specific privacy requirements.
The API supports multiple anonymization strategies. Redaction completely removes or masks sensitive data by replacing it with placeholders like [PERSON] or [EMAIL]. Pseudonymization replaces real values with consistent fake values, maintaining data structure and relationships for analytics while protecting privacy. For example, 'john@acme.com' might become '[EMAIL]' (redaction) or 'user123@example.com' (pseudonymization). You can specify your preferred approach based on whether you need to preserve data utility for analysis or completely eliminate sensitive information.
Keep building