Semantic search returns works whose meaning is closest to your query, even when the wording differs. A query about “predicting drug toxicity from molecular structure” finds papers using “computational toxicology” or “QSAR” — words your search never mentioned.Documentation Index
Fetch the complete documentation index at: https://developers.openalex.org/llms.txt
Use this file to discover all available pages before exploring further.
Long-text queries
Semantic search shines when you have a longer description — an abstract, a grant aim, or a paragraph from a paper you’re writing. The richer the input, the better the matches.Combining with filters
Most filters and theselect parameter work as usual:
last_known_institutions.country_code(and thecountry_codeshorthand)cited_by_count
How it works
OpenAlex embeds the title and abstract of every work using GTE Large EN, an open-source embedding model from Alibaba DAMO Academy, into a 1,024-dimensional vector. At query time we embed your query the same way and return the works closest by cosine similarity.Limits
| Constraint | Value |
|---|---|
| Max input length | 2,000 characters |
| Max results | 50 per query |
| Rate limit | 1 request per second |
| Pricing | See pricing by endpoint |
Only one search parameter is allowed per request:
search, search.exact, or search.semantic.