text

search arxiv papers by query with field prefixes, boolean operators, category filtering, and sorting

search biorxiv and medrxiv preprints by date range with optional category filtering

search chemrxiv preprints via crossref api

get a specific arxiv paper by its id with full metadata including title, authors, abstract, and links

get a chemrxiv paper by doi via crossref api

get a specific biorxiv or medrxiv paper by its doi

domain research api — search for available domains and check registration status

web search powered by ceramic ai

web search api — ground your apps in reliable, web-scale knowledge with contextual snippets

tavily-powered search assistant that browses the internet and returns comprehensive results. searches the web using tavily api with configurable depth, filters, and includes ai-generated answers, images, and detailed sources.

intelligent web search using exa's neural and keyword search capabilities

download a file from an internet archive item

get item metadata from the internet archive

search the internet archive

check url availability in the wayback machine

contents api — fetch clean markdown or html from any url, batch up to 10 pages per request

extracts clean, readable content, including text and images, from specified webpages, supporting batch processing for multiple urls.

extract and analyze web page content using exa's advanced content retrieval

finance research api — agentic financial research with filings, macro data, and institutional-grade sources

deep research api — multi-step web research with source-backed citations and configurable effort levels

generate llm-powered answers informed by exa search results

next-gen document ocr with improved math, tables, and reading order. converts images and pdfs to structured markdown.

extracts and converts text from documents, especially good at reading images, photos, handwriting, charts, and graphs.

convert markdown text or files to word (.docx) documents

multilingual text embedding using microsoft's harrier oss v1 models. supports retrieval, clustering, semantic similarity, classification, and reranking with state-of-the-art mteb v2 scores.

generate structured prompt json from text or images using bria

runs and executes python programming code in a safe environment.