Plant.id API is machine learning plant identification
Doing business in agriculture, the environment, or a smart garden and need to identify plants? We offer our identification engine over an API and custom solutions to fit your needs.
- Unlimited scalability
- Easy integration
- Complex plant info
Model specification
12 000+
Identifiable plant species
Our newest model can identify 12 183 plant species. The set covers the most commonly requested plants from the United States, Europe, India, and Australia.
89.9%
Success rate
We are continually testing model accuracy. The average success rate ranges between 80%–90%, although it strongly depends on photo and plant quality. Our goal is to improve the average over 89.9% while extending the spectrum of identified species.
Features
Similar images
Get representative images of suggested plant species. Photos are dynamically generated to resemble your photo. We provide you with a license to these photos so you can use them in your application.
Plant information
You will get additional information about suggested species, like taxonomy, description, common names in different languages, edibility, propagation methods, Wikipedia link, and more. See all available details in the documentation.
Plant health assessment
Plant.id can identify 100 plant diseases. Use one of the health assessment modifiers in the request to get info about the health condition of your plant. See more details about the Health Assessment feature.
All the identification data packed into JSON
Send us photos of the plant in a POST REST API request and you will get multiple plant species suggestions in the JSON formatted response. Apart from the scientific name of the species, you can also get common names, similar images, taxonomy, and much more information about possible species.
Check the sample codes on GitHub in different programming languages.
"suggestions":[
{
"id":148452111,
"plant_name":"Taraxacum officinale",
"plant_details":{
"common_names":[
"common dandelion"
],
"edible_parts":[
"flowers",
"leaves"
],
"propagation_methods":[
"division",
"seeds"
],
"synonyms":[
"Chondrilla taraxacum",
"Leontodon taraxacum"
],
"taxonomy":{
...
Technology
To provide the best results of our plant identification API, our tech stack uses Google’s TensorFlow and a python-based heavy lifting. A minor part of the service is based on Google Cloud and Microsoft Azure.
The neural network’s architecture is based on the Inception model, but we have implemented a bunch of customization, for example, to estimate identification certainty, select the best adaptive representative photos and improve the accuracy with meta attributes like GPS coordinates.
Pricing & Payment
The base price is €0.05 per request. There are significant discounts for higher volumes of identifications. Tell us what you need on business@plant.id.
We provide prepaid and retroactive models. You can pay with a card, wire transfer, or PayPal.
Future plans
We are continuously improving the Plant.id API. Our researchers and developers use cutting-edge machine learning methods to improve the model accuracy. We also reflect the recent changes in the botanical taxonomy and trends. We regularly add new content about the plant species.
- Health assessment – Detect the plant diseases from the image data.
- Object detection – Provide bounding boxes for different plant species within a single image.
- Varieties, subspecies, and cultivars identification