A pretrained highlighted text classifier that sorts an image into one of 2 categories. Use the highlighted text API immediately, no training required, then adapt it to your own data when you need more.
Drop in a photo and get the prediction back. No signup, no setup.
A sample of the 2 labels this pretrained classifier chooses between.
Need a label that isn't here? Clone the classifier into your Nyckel console and edit the label set to fit your data.
Once you've added this classifier to your console, you get your own copy of it behind your own endpoint. Invoke it with any HTTP client:
curl
curl -X POST "https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke" \
-H "Authorization: Bearer $NYCKEL_ACCESS_TOKEN" \
-H "Content-Type: application/json" \
-d '{"data": "https://example.com/photo.jpg"}'Python
import requests
# Get an access token: https://www.nyckel.com/docs/api/overview/authentication/
token = "YOUR_ACCESS_TOKEN"
response = requests.post(
"https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke",
headers={"Authorization": "Bearer " + token},
json={"data": "https://example.com/photo.jpg"},
)
print(response.json())Example response
{
"labelName": "Highlighted",
"labelId": "label_...",
"confidence": 0.92
}Trained on a Nyckel-curated dataset covering 2 highlighted text categories, served on Nyckel's own infrastructure — your image stays on Nyckel.
Send an image URL or file to the invoke endpoint; the response is a label with a confidence score.
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.
This function can be employed in the legal sector to automatically identify highlighted text in contracts and agreements. By streamlining the review process, legal professionals can focus on critical sections of documents, enhancing efficiency and reducing the risk of missing important information.
Educational platforms can use this feature to scan and evaluate student assignments for critical quotes or highlighted material. This can augment feedback mechanisms, ensuring that educators can provide targeted advice based on the most emphasized concepts by students.
Marketers can implement this function to analyze customer feedback and insights documents where certain points are highlighted. This can help extract key trends and preferences more effectively, guiding content creation and promotional strategies.
Software applications that support text editing could leverage this function to improve user experience by making it easier to locate highlighted text within documents. This would save users time and make interactions more intuitive, particularly for large volumes of text.
Academic researchers can utilize this functionality to process numerous research papers and extract highlighted findings or key arguments. This would significantly enhance literature review processes, allowing researchers to synthesize information quicker and more accurately.
Financial institutions can employ this binary classification function to monitor highlighted text within regulatory documents. By ensuring that specific regulations or compliance-related highlights are accurately identified, organizations can reduce risks associated with non-compliance.
Media organizations can use this capability to scan articles for highlighted quotes or statements from sources. This can help journalists quickly identify key themes or trends in reporting, facilitating deeper analysis and more insightful storytelling.
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.
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 images 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.
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.
No. This highlighted text 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.
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.
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.