Diagnose with plant.health

Integrate plant.health into your business and discover the world of AI-powered disease identification and plant care.

Plant care made easy

Plant.health offers disease diagnosis from images, utilizing hundreds of thousands expert-annotated data. It provides multilingual options for developers and R&D teams to craft innovative and user-centric solutions.

548 classes of abiotic disorders, pests, diseases and non-harmful look-alikes

Localized common names, descriptions and treatment

License for representative images

Unlimited scalability

Fungi
Confidence: 91%
plant.health

Excellent precision

Recognizing the complexity of plant diseases, we work with top plant pathologists to annotate photos of diseased plants. This allows us to go beyond mere symptoms and diagnose the actual disease, achieving unparalleled specificity and confidence.

548
Access carefully selected plant-health conditions: pests, diseases (fungal, bacterial, viral), abiotic disorders and non-harmful look-alikes.
60%
Get the correct diagnosis in almost two-thirds of queries within the top three results.

Care for the future

We constantly improve the plant.health API. In 2025, we have exciting update designed to elevate your experience.

By clicking Keep me updated you're confirming that you agree with our Privacy Policy.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Let's plant the next big success together!

Enhance your applications with our cutting-edge plant identification technology. Captivate your users and transform their experience with plant.health. Your journey starts now.

FAQs

Find answers to common questions about plant.health here. If you need further information, feel free to reach out.

Can I only get disease identification when a plant is sick?

We also provide an is_healthy model that can identify whether a plant is healthy or diseased. Besides, you can also use the health=auto attribute to decide whether an image should undergo a health diagnosis automatically; if the model’s output for a harmful or non-harmful condition exceeds a specific threshold, the full plant-health response is returned. In this case, the cost is two credits.

If you want responses from both plant.id and plant.health, you can set the parameter health=all. The total cost is two credits.

What is the total cost of identifying diseases?

The cost is one identification credit, the same as for plant identification. In case you want both the plant.id and plant.health results for a single plant, the cost is one credit for each product. The base price is €0.05 per credit. Discounts are available for bulk orders. Contact business@plant.id for details.

Sometimes the result incorrectly states that the plant is healthy or identifies the wrong disease. What am I doing wrong?

Diagnosing plant health is often a complex task. For example, if a plant is consistently overwatered, it is also unable to use nutrients effectively, so it will develop symptoms of both overwatering and nutrient deficiency. Therefore, when implementing this functionality, we recommend that you list more than one possible cause of disease in the result.

However, you can improve the results by encouraging your users to take a photo of the diseased part of a plant. Some diseases have less visible symptoms, such as small pests, and capturing the necessary detail is crucial for correct identification.

I do not need 500+ diseases, can I get more general results?

You can spefify the disease_level = general to get only general classes.

What is the difference between crop.health and plant.health?

Plant.health does not focus on a specific group of plants, although most annotations are for houseplants and ornamentals. Crop.health focuses on a broad range of diseases of selected food crops. You can read more about the differences in the crop.health FAQ section.

Expand FAQ