Provenance

Where this comes from

Every claim on this site traces to a dataset named below. Where we do not have something, the page that would have carried it says so, rather than filling the gap with prose that sounds right.

Datasets3 in production

World Flora Online Plant List

Accepted names, authorities, synonymy, family and genus placement. The taxonomic spine of the entire site.

The CC0 covers nomenclature and classification only. It does not cover descriptions or images, and we do not treat it as though it does.

Release
2026-06
Synced
2026-07-12
382,386 accepted species, 1,026,245 synonyms

iNaturalist open data

Photographs, and the flowering annotations behind every phenology chart. Ground truth for our identification benchmark.

We scanned all 132 million photographs in the archive. 76.5% carry a NonCommercial licence. This site is commercial, so we cannot use them, and we do not.

Release
Dump of 2026-06-27
Synced
2026-07-13
6,736,889 commercially usable plant photographs

Google AIY plants V1

The on-device identification model in the BotanAI app, and the source of the confusion data behind our lookalike pages.

We publish this model’s error rate, including the parts that are unflattering. See the accuracy benchmark.

Licence
Apache 2.0
Release
V1
Synced
2026-07-13
2,102 classes

What we do not havethe honest part

A provenance page that lists only strengths is marketing. These are the gaps, and they are visible on the pages themselves.

Native range
Not yet published. We are building it from Kew’s WCVP (CC BY 4.0) joined to WGSRPD level-3 regions. Until it exists, the field on every species page reads "not yet sourced".
Care advice
Not published. Every care claim we could make cheaply would be an unsourced enum, which is what the previous version of this site did and why it was deleted.
Toxicity
Not published. The widely copied list is a copyrighted compilation and we will not scrape it. We are rebuilding toxicity from primary veterinary and toxicological literature, with the toxic principle and the reference named per claim. It ships last, and it ships reviewed.
Botanical review
No page on this site has been reviewed by a named botanist. The determination label says so, on every page.
Species coverage
We publish 2,057 species today, growing toward 56,848. That is the number that clears our evidence gate, not the number of plants that exist. Roughly 300,000 accepted species have no commercially usable photograph anywhere, and we would rather omit them than publish an empty page about them.

Attributionhow we credit

Every photograph on this site carries its photographer’s name, its licence, and a link back to the observation it came from, rendered visibly under the image rather than hidden behind a tooltip. The same information is emitted as machine-readable metadata on every page.

Images licensed CC BY-SA are never cropped or composited, because a share-alike licence bites on adaptations. They render whole, letterboxed, or not at all.

Correctionstell us

If something here is wrong, we want to know, and we will say what changed and when. Write to support@botanai.app.