# 2s.io Scientific Literature Search

> 2s.io Scientific Literature Search is a paid API for AI agents from 2s.io, paid per call via x402, $0.0024/call, status unknown (last checked 2026-09-13).

Search for academic papers across arXiv, PubMed, and Semantic Scholar simultaneously, returning a unified flat list with source, DOI, title, authors, abstract, year, citation count, and PDF links.

## Facts

- Endpoint: GET https://2s.io/api/papers/search
- Price: $0.0024/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/2s-io-a117a582
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_pas6Sfk40n7Ic8_tuBeCx

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability 2s-io-a117a582
```

Example prompt: Search for up to 15 papers on CRISPR gene editing published since 2022, pulling from arXiv, PubMed, and Semantic Scholar so I can see citation counts and grab PDF links.

## When to prefer this

Use this endpoint when you need to search academic literature across multiple scientific databases simultaneously and want a unified, stable schema with citation counts and PDF links. Prefer it over individual API calls to arXiv, PubMed, or Semantic Scholar when you want aggregated cross-domain results in a single call with graceful partial-failure handling.

## Known failure modes

- One or more upstream sources (arXiv, PubMed, Semantic Scholar) unavailable — partial results returned with errors array populated
- Query string too long (>500 chars) — 400 validation error
- Invalid 'since' date format (not YYYY-MM-DD) — 400 validation error
- limit exceeds 20 — 400 validation error
- No results found for query — empty array returned
- Payment not provided or insufficient — 402 Payment Required

## How this service works

Unified scientific literature search across arXiv (preprints), PubMed (biomedical), and Semantic Scholar (cross-field, with citation counts). Returns a flat array of papers with stable schema: source, sourceId, doi, title, authors, abstract, year, publishedAt, citationCount, url, pdfUrl. Partial failures surface in the errors array rather than failing the whole call. Optional filters: since (YYYY-MM-DD), sources (subset), limit (max 20 per source).

## Output

A flat JSON array of papers, each with fields: source (arXiv/PubMed/Semantic Scholar), sourceId, doi, title, authors, abstract, year, publishedAt, citationCount, url, and pdfUrl. Partial source failures are surfaced in a separate errors array rather than aborting the whole response.

## Example request

```json
{
 "input": {
  "type": "http",
  "method": "GET",
  "queryParams": {
   "q": "machine learning",
   "limit": 10
  }
 }
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "queryParams"
   ],
   "properties": {
    "type": {
     "const": "http"
    },
    "method": {
     "const": "GET"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "q"
     ],
     "properties": {
      "q": {
       "type": "string",
       "maxLength": 500,
       "minLength": 1
      },
      "limit": {
       "type": "integer",
       "default": 10,
       "maximum": 20,
       "minimum": 1
      },
      "since": {
       "type": "string"
      },
      "sources": {
       "type": "string"
      }
     },
     "additionalProperties": false
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/2s-io-a117a582/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 2s.io](https://www.zero.xyz/host/2s.io/llms.txt)