Every paper, every section, one call each.
Full-text arXiv synced the day it is announced, plus PMC, bioRxiv and medRxiv. Hybrid retrieval that filters like a database, an agentic loop that reads sections and answers with real IDs.
| Source | Scale | Depth | Freshness |
|---|---|---|---|
| arXiv | 3,166,878 papers | Full text, sectioned, hybrid-indexed | T+0 — same day as announcement |
| PubMed Central | ~7.5M articles | Structured parse, section access | Daily |
| bioRxiv / medRxiv | Preprint corpus | Section access, same reading verbs | Daily |
Three questions it answers well
Click one to open it in the playground.
Read in layers, not all at once
An agent deciding whether a document is worth reading shouldn’t pay for the whole document. Each layer is a separate call, cheap enough to run across the full candidate set. Real numbers.
2409.05591Judging whether this paper is worth reading costs 300 tokens, not 23,311 — 78× less.
Search that filters like a database
Author, organisation, category, venue (NeurIPS ↔ NIPS aliases resolve), venue year, date ranges, minimum citations, offset paging, opt-in fine reranking. Filters combine with AND — a narrow date window on a high citation floor can legitimately return zero.
Trending, by social signal
What is actually being read right now — per-paper tweets, likes and views.
Beyond arXiv
PubMed Central, bioRxiv and medRxiv share the same reading verbs. Open-access only.
Two agentic backends
arXiv answers with paper IDs; the web backend answers with URLs from cached page bodies, marking which were read in full.
Effort levels
| Effort | Gather rounds | First token · arXiv | First token · web | Reach for it when |
|---|---|---|---|---|
| default | 1–2 | 3–4s | 5–9s | You want an answer now |
| high | 3 | 7–8s | ≈13s | Comparing across papers |
| xhigh | 4–5 | 9–13s | longer | Survey-shaped questions |
Three things to know before you wire this into an agent
An agent handed a bare ask(query) tool will use this API poorly. These three distinctions belong in your tool descriptions.
Citations are real
Never invents an arXiv ID, an article number or a case number — it says nothing relevant rather than fabricate. Tell your agent to preserve them in what it reports back.
Sources ≠ citations
A ten-document retrieval often supports one citation. sources is the retrieval set — filter to IDs that appear in the answer, or your agent will present unrelated documents as evidence.
Truncation is flagged, not hidden
Hit max_answer_tokens and the API sets answer_truncated. Surface it, or an agent will summarise a cut-off answer as though it were whole.