Web Search Research x402 offerings

Research brief. Citations. Summarize research from the public web with key points and caveats. When to use: short cited answers for agent questions (fair-use snippets only — no full-text dumps). $0.08 per call in USDC on Base via x402 (cost-floored). No API key.

Research brief. Citations. Summarize research from the public web with key points and caveats. When to use: short cited answers for agent questions (fair-use snippets only — no full-text dumps). $0.0…

Wikipedia summary: the Wikipedia summary and lead section for a page title in any language, with the CC BY-SA 4.0 licence, the article URL and the authors link. Use when you need to answer: What does Wikipedia say about this topic? Cached 24 hours.

Page or PDF summary: a short or medium summary with key points, and says whether the document was cut at 20,000 tokens and how much was read. Use when you need to answer: What does this page or PDF say, in short? Uses only what the document says.

Web page to markdown: the main content of the one URL you pass as clean markdown (Mozilla Readability, then turndown), with title, final URL, fetch time and word count. http or https on ports 80 and 443, 5 MB, 10 s; robots.txt honoured and private addresses refused. Use when you need to answer: What does this web page say, as clean markdown? A blocked or unreachable URL is never charged.

Web search for AI agents: query in, ranked results out (title, URL, snippet) as clean JSON. Sovereign metasearch — no API key, no upstream account. Also does news search (type=news). Priced to undercut the incumbents.

Token-efficient web reader: URL in, clean deduplicated article markdown out, with token count header. Boilerplate, nav, ads stripped — typically 10-30x fewer tokens than raw HTML. For AI agents that pay per token.

Scrape a URL and return markdown, links, metadata, and tech stack. Falls back to Firecrawl if needed. 1 credit.

Get recent news articles for a specific company or the broad market. Pass a ticker for company-specific news, or omit the ticker for general market news.

Google News search - returns news articles with titles, links, sources, dates, and snippets. Use for current events, press coverage, competitor monitoring, or media research. Pagination billing: call the first page normally and save billing.requestId from the Orthogonal /v1/run response. For later page, offset, or cursor calls on the same logical search, pass parentRequestId with unchanged non-pagination parameters. Valid continuation calls still get their own request IDs and quoted price, but are charged 0. Changing filters starts a new billable request.

Runs a search, scrapes the top N result URLs, optionally runs LLM extraction with prompt and schema.

Fast, high-quality search API with intelligent ranking, instant answers, and result enrichment.

Retrieve search results or queue a search for later retrieval. Supports Google engine with geotargeting by country, subdivision, and city. Returns structured SERP data. Pagination billing: call the first page normally and save billing.requestId from the Orthogonal /v1/run response. For later page, offset, or cursor calls on the same logical search, pass parentRequestId with unchanged non-pagination parameters. Valid continuation calls still get their own request IDs and quoted price, but are charged 0. Changing filters starts a new billable request.

Google Search - returns organic results, knowledge graph, people also ask, related searches, and sitelinks. Use for general web queries, fact-finding, and research. Pagination billing: call the first page normally and save billing.requestId from the Orthogonal /v1/run response. For later page, offset, or cursor calls on the same logical search, pass parentRequestId with unchanged non-pagination parameters. Valid continuation calls still get their own request IDs and quoted price, but are charged 0. Changing filters starts a new billable request.

Search the web and return matching documents with URLs and content.

Count the number of results matching search filters without returning the actual data.

Performs an intelligent web search. Costs 1 credit per returned result.

Fetches a URL and returns the requested format(s): markdown, html, links, images, summary, json, branding, screenshot. | ERROR: Unable to calculate price.

Scrapes the given URL, converts the HTML content to Markdown, and returns the result.

Performs advanced web search queries and returns relevant results.

Summarize a passage of text into a short, concise summary with no preamble (qwen3.5 2B model). Good for condensing articles, emails, logs or documents before passing them to another agent. POST JSON {"input": string}, up to 3000 characters; returns {summary, model, elapsed_ms}. Typically 5-15 s. Small model: may miss nuance in technical or long text. Text only.

x402engine — Scrape any URL and get clean markdown content — ideal for extracting readable text from web pages

x402engine — Capture a screenshot of any URL — returns base64-encoded image, supports full-page capture

x402engine — Fetch full text content from URLs — extract clean text from up to 10 pages at once