Pretrained text classifier

Identify if phone number is in a message with one API call.

A pretrained if phone number is in a message classifier that sorts text into one of 2 categories. Use the if phone number is in a message API immediately, no training required, then adapt it to your own data when you need more.

Use this classifier Try with your text snippet

Pretrained · Nyckel-trained 2 labels out of the box Text input

nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke

Contains Phone Number 0.92

Does Not Contain Phone Number 0.05

Try the if phone number is in a message classifier

Drop in some text and get the prediction back. No signup, no setup.

What this if phone number is in a message classifier recognizes

A sample of the 2 labels this pretrained classifier chooses between.

Contains Phone Number

Does Not Contain Phone Number

Need a label that isn't here? Clone the classifier into your Nyckel console and edit the label set to fit your data.

Call the if phone number is in a message API

Get your own copy of this classifier behind your own endpoint — callable from any HTTP client:

API quick start

curl -X POST "https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"data": "The text you want to classify"}'

import requests

response = requests.post(
    "https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke",
    headers={"Authorization": "Bearer YOUR_ACCESS_TOKEN"},
    json={"data": "The text you want to classify"},
)
print(response.json())

const response = await fetch("https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_ACCESS_TOKEN",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ data: "The text you want to classify" }),
});
console.log(await response.json());

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, 'https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, '{"data": "The text you want to classify"}');

$headers = array();
$headers[] = 'Authorization: Bearer YOUR_ACCESS_TOKEN';
$headers[] = 'Content-Type: application/json';
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

$result = curl_exec($ch);
curl_close($ch);
echo $result;

Create free account to get your live API key Clone this function to get a live API key

How to invoke a function →

Example response

{
  "labelName": "Contains Phone Number",
  "labelId": "label_...",
  "confidence": 0.92
}

API documentation Authentication Pricing Get your endpoint

Under the hood

Model type

Nyckel-trained

Trained on a Nyckel-curated dataset covering 2 if phone number is in a message categories, served on Nyckel's own infrastructure — your text snippet stays on Nyckel.

Input

Text

Send raw text to the invoke endpoint; the response is a label with a confidence score.

Make it yours

Adaptable

Clone it, then correct predictions and add your own samples in the console — Nyckel retrains automatically, turning this into a custom model tuned to your data.

More than a demo: this page is one of thousands of pretrained functions on Nyckel, an ML classification platform. You can invoke classifiers by API, review predictions, correct labels, collect samples from production traffic, and promote any pretrained function to a private custom model — without changing your integration.

Where teams use if phone number is in a message classification

Customer Support Automation

This function can be integrated into customer support chatbots to identify messages containing phone numbers. By extracting this information, support teams can quickly escalate issues to human agents or initiate follow-up calls to improve response times.

Lead Generation Tracking

Sales teams can utilize this identifier in their lead tracking systems to monitor customer inquiries containing phone numbers. By flagging these messages, companies can prioritize leads for follow-up and increase conversion rates.

Fraud Detection

Financial institutions can implement this function to monitor incoming messages for phone numbers that may indicate fraudulent activity. By identifying suspicious patterns, the system can alert security teams to investigate further and take protective measures.

Marketing Campaign Optimization

Businesses can analyze messages for phone numbers to optimize marketing campaigns. By understanding which campaigns generate the most inbound phone communication, companies can refine their marketing strategies and improve targeting efforts.

Data Quality Assurance

Organizations can use this identifier to clean up their databases by identifying messages that may contain erroneous or outdated phone numbers. By flagging these entries, teams can take action to verify and update contact information, enhancing overall data quality.

Regulatory Compliance

Companies in regulated industries can employ this function to ensure compliance with laws regarding the handling of sensitive information, such as phone numbers. By tracking messages that contain such data, organizations can maintain records and provide necessary audits for regulatory bodies.

User Privacy Monitoring

This function can assist companies in implementing user privacy protocols by detecting messages that contain personal information like phone numbers. By monitoring and addressing this data, organizations can uphold privacy regulations and enhance consumer trust.

Common questions

What's the difference between a zero-shot and a Nyckel-trained classifier?

A zero-shot classifier uses a large foundation model's general knowledge to pick between your labels — no task-specific training, so new or edited labels work immediately. A Nyckel-trained classifier has been trained on labeled examples and runs on Nyckel's own infrastructure, which typically makes it faster, cheaper per call, and more accurate on data that resembles its training set. The "Under the hood" section on this page shows which kind this classifier is, and any classifier can be adapted into a trained one by adding your own examples.

How do I know whether this will work for my application?

Honestly: we can't know in advance — it depends on your data stream and how closely it resembles what this classifier has seen. The reliable way to find out is to measure it on your own data: start invoking the classifier with real traffic, or upload and annotate a set of text samples in the console — make sure they look like your production data, not idealized examples. Nyckel's evaluation metrics then show you exactly how it performs on that data before you rely on it.

What happens when it makes a mistake?

No classifier is perfect, so Nyckel is built around the correction loop: invokes can be captured for review, you confirm or correct predictions in the console, and corrections become training data. Over time the model adapts to your data distribution — accuracy on your traffic improves with use rather than staying fixed.

Do I need training data to get started?

No. This if phone number is in a message classifier works out of the box — clone it into your console and you'll have your own API endpoint in under a minute. Training data only enters the picture when you want to adapt it: your corrected predictions and uploaded samples improve the model, and you can also edit the label set to match your needs.

What does it cost to try?

Trying the classifier on this page is free with no signup. Cloning it requires a free account, and the free tier covers your first API calls each month — see nyckel.com/pricing for current limits and paid tiers.

Related classifiers

Ready to classify if phone number is in a message at scale?

Add this pretrained classifier to your Nyckel console — you'll get a live API endpoint in under a minute, and a path to a custom model when you need one.

Use this classifier Read the docs