# BlockRun.AI Web Search

> BlockRun.AI Web Search is a paid API for AI agents from blockrun.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Neural and keyword web search with optional category filters including company, research paper, news, PDF, GitHub, tweet, personal site, LinkedIn profile, and financial report.

## Facts

- Endpoint: POST https://blockrun.ai/api/v1/exa/search
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/blockrun-ai-3c71ed29
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_aqq7sINe8wSm-5qItJai3

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 blockrun-ai-3c71ed29 -d '<json body>'
```

Example prompt: Search the web for recent research papers about transformer architecture scaling laws and return 5 results — filter to the 'research paper' category only.

## When to prefer this

Choose this endpoint when you need neural (semantic) or keyword web search with fine-grained category filtering (e.g. only research papers, only tweets, only LinkedIn profiles, only financial reports). Prefer it over generic search APIs when the content type matters and you want structured result metadata like publish date and image preview.

## Known failure modes

- Invalid or unsupported category filter value returns an error
- numResults exceeding 100 may be rejected or capped
- Empty query string may return an error or empty results
- Payment failure (402) if USDC balance is insufficient
- Conflicting includeDomains and excludeDomains may produce empty results

## How this service works

Neural and keyword web search. Optional category filter: company, research paper, news, pdf, github, tweet, personal site, linkedin profile, financial report.

## Output

Returns a list of search results, each containing a result ID, URL, page title, published date, and optionally a favicon and image preview thumbnail.

## Example request

```json
{
 "query": "machine learning applications",
 "category": "research paper",
 "numResults": 5
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "query": {
   "type": "string",
   "description": "Natural-language search query."
  },
  "category": {
   "type": "string",
   "description": "Optional category filter: company, research paper, news, pdf, github, tweet, personal site, linkedin profile, financial report."
  },
  "numResults": {
   "type": "number",
   "description": "Number of results to return (default 10, max 100)."
  },
  "excludeDomains": {
   "type": "array",
   "description": "Exclude these domains from results."
  },
  "includeDomains": {
   "type": "array",
   "description": "Restrict results to these domains."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/blockrun-ai-3c71ed29/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from blockrun.ai](https://www.zero.xyz/host/blockrun.ai/llms.txt)