Search academic literature across OpenAlex, Crossref and arXiv in one call: title, authors
Search academic literature across OpenAlex, Crossref and arXiv in one call: title, authors, year, venue, DOI, citation count, abstract and a DIRECT open-access PDF link where one exists. Deduplicated across sources, filterable by year and open-access, optional BibTeX per paper. One request replaces three APIs.
10000 (raw units)
price
1
calls / 30d
1
unique payers
2026-09-06
updated
Provider
agentbit.app · discovered, not yet claimed by its owner
Payment (x402 accepts[])
[
{
"scheme": "exact",
"network": "eip155:8453",
"payTo": "0x4395C7e383b7e05665aad7f36ed77c01923Dd965",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "10000",
"maxTimeoutSeconds": 300
}
]Output schema
{
"bazaar": {
"info": {
"description": "Academic paper search built for AI agents doing real research. One paid call queries three authoritative open scholarly indexes simultaneously — OpenAlex (250M+ works with citation counts and open-access resolution), Crossref (the DOI registry) and arXiv (preprints with guaranteed PDFs) — then merges and deduplicates the results by DOI and title. Each paper returns: title, up to 12 authors, publication year, venue, DOI, citation count (richest source wins), a reconstructed abstract where available, the canonical URL, and — the part agents actually need — a direct open-access pdf_url when a legal free full text exists, so the next step (fetch and read the paper) is one HTTP GET away. Filters: limit (1-25), year_from, open_access_only. Set format to 'bibtex' to also get a ready-to-use BibTeX entry per paper. Per-source status is reported so you can see exactly which indexes answered. Data comes from public scholarly APIs; citation counts and OA links are as fresh as the sources themselves.",
"errors": [
{
"code": "PAYMENT_REQUIRED",
"description": "Missing or invalid payment — retry with a valid PAYMENT-SIGNATURE header",
"retryable": true,
"status": 402
},
{
"code": "VALIDATION_ERROR",
"description": "Request body does not match the input schema",
"retryable": false,
"status": 422
},
{
"code": "RATE_LIMITED",
"description": "Too many requests from this client",
"retryable": true,
"status": 429
},
{
"code": "UPSTREAM_TIMEOUT",
"description": "Upstream data source unavailable — safe to retry",
"retryable": true,
"status": 502
}
],
"input": {
"body": {
"format": "bibtex",
"limit": 5,
"query": "attention is all you need transformer"
},
"bodyType": "json",
"method": "POST",
"type": "http"
},
"networks": [
"eip155:8453"
],
"output": {
"example": {
"note": "Merged and deduplicated across OpenAlex, Crossref and arXiv; citations from the richest source; pdf_url is a direct open-access link where one exists.",
"papers": [
{
"abstract": "The dominant sequence transduction models are based on complex recurrent or convolutional neural networks...",
"authors": [
"Ashish Vaswani",
"Noam Shazeer",
"Niki Parmar"
],
"bibtex": "@article{vaswani2017,\n title = {Attention Is All You Need},\n author = {Ashish Vaswani and Noam Shazeer and Niki Parmar},\n year = {2017}\n}",
"citations": 100000,
"doi": "10.48550/arxiv.1706.03762",
"pdf_url": "https://arxiv.org/pdf/1706.03762",
"sources": [
"openalex",
"arxiv"
],
"title": "Attention Is All You Need",
"url": "https://doi.org/10.48550/arxiv.1706.03762",
"venue": "Neural Information Processing Systems",
"year": 2017
}
],
"query": "attention is all you need transformer",
"result_count": 5,
"sources": {
"arxiv": {
"ok": true,
"results": 15
},
"crossref": {
"ok": true,
"results": 15
},
"openalex": {
"ok": true,
"results": 15
}
}
},
"type": "json"
},
"pricing": {
"amount": 0.01,
"currency": "USDC",
"firstCallFree": true,
"model": "per-call",
"quoteHint": "Send your wallet address in an X-BUYER-WALLET header on the unpaid request to receive your personalized (volume-discounted) quote.",
"volumeDiscounts": [
{
"minCalls30d": 100,
"percent": 10
},
{
"minCalls30d": 1000,
"percent": 20
}
]
},
"reliability": {
"measuredAt": "2026-09-06T13:15:31+00:00",
"p50LatencyMs": 4537,
"p95LatencyMs": 4537,
"sampleSize": 1,
"successRatePercent": 100,
"windowDays": 30
}
},
"schema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"description": {
"type": "string"
},
"errors": {
"items": {
"properties": {
"code": {
"type": "string"
},
"description": {
"type": "string"
},
"retryable": {
"type": "boolean"
},
"status": {
"type": "integer"
}
},
"required": [
"status",
"code"
],
"type": "object"
},
"type": "array"
},
"input": {
"additionalProperties": false,
"properties": {
"body": {
"description": "Academic Paper Search input. Search academic literature across OpenAlex, Crossref and arXiv in one call: title, authors, year, venue, DOI, citation count, abstract and a DIRECT open-access PDF link where one exists. Deduplicated across sources, filterable by year and open-access, optional BibTeX per paper. One request replaces three APIs.",
"properties": {
"format": {
"description": "'bibtex' adds a ready-to-cite BibTeX entry per paper",
"enum": [
"json",
"bibtex"
],
"type": "string"
},
"limit": {
"description": "Max papers to return (1-25, default 10)",
"type": "integer"
},
"open_access_only": {
"description": "Only papers with a direct open-access PDF link",
"type": "boolean"
},
"query": {
"description": "Search query: topic, title fragment, or author + topic (3-300 chars)",
"type": "string"
},
"year_from": {
"description": "Only papers published in or after this year",
"type": "integer"
}
},
"required": [
"query"
],
"type": "object"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"headers": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"method": {
"enum": [
"POST",
"PUT",
"PATCH"
],
"type": "string"
},
"queryParams": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"networks": {
"items": {
"type": "string"
},
"type": "array"
},
"output": {
"properties": {
"example": {
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
},
"pricing": {
"properties": {
"amount": {
"type": [
"number",
"null"
]
},
"currency": {
"type": "string"
},
"firstCallFree": {
"type": "boolean"
},
"maxAmount": {
"type": "number"
},
"model": {
"type": "string"
},
"quoteHint": {
"type": "string"
},
"volumeDiscounts": {
"items": {
"properties": {
"minCalls30d": {
"type": "integer"
},
"percent": {
"type": "number"
}
},
"required": [
"minCalls30d",
"percent"
],
"type": "object"
},
"type": "array"
}
},
"type": "object"
},
"reliability": {
"properties": {
"measuredAt": {
"type": "string"
},
"p50LatencyMs": {
"type": [
"integer",
"null"
]
},
"p95LatencyMs": {
"type": [
"integer",
"null"
]
},
"sampleSize": {
"type": "integer"
},
"successRatePercent": {
"type": "number"
},
"windowDays": {
"type": "integer"
}
},
"required": [
"successRatePercent",
"sampleSize",
"windowDays"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}
}
}Use it
curl
curl "https://agentbit.app/v1/research/papers" # -> 402 Payment Required, accepts[] lists how to pay # retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid
JavaScript
const res = await fetch("https://agentbit.app/v1/research/papers");
if (res.status === 402) {
const { accepts } = await res.json();
// pay one of accepts[] via an x402 client, then retry with the payment header
}Python
import httpx
res = httpx.get("https://agentbit.app/v1/research/papers")
if res.status_code == 402:
accepts = res.json()["accepts"]
# pay one of accepts[] via an x402 client, then retry with the payment headerMachine-readable
Everything on this page is also available as clean JSON at /resources/10996.json, and this resource appears in /discovery/resources and /discovery/search.