Web Search Research x402 offerings

Podcast search: a podcast name or Apple Podcasts link to its RSS feed URL, show data and latest episodes (utilpeek by Tanod). Use when an agent must find a podcast's RSS feed URL and latest episodes …

Search the web: ranked title, URL and query-dependent snippet per result from an independent web index (Mojeek), with short-lived caching (findpeek, Tanod). Results are third-party web content. Use w…

sitepeek (Tanod) page links: a public page's links classified internal, external, anchor, mailto or tel, with anchor text and rel flags. Read-only.

sitepeek (Tanod) PDF text: the text and document metadata of a public PDF (up to 200 pages), parsed in an isolated, resource-limited process. Read-only.

sitepeek (Tanod) page metadata: title, description, canonical, Open Graph and Twitter tags, icons, RSS/Atom feeds, JSON-LD types, headings and link counts of a public page (static HTML). Read-only.

mlpeek (Tanod) rerank: up to 100 documents scored against a query (cross-encoder).

Use when an agent must decide which crypto stories to react to: top headlines ranked by outlet coverage, new ones only. utilpeek (Tanod) ranked crypto news headlines from seven outlets: stories group…

sitepeek (Tanod) sitemap: the URLs of an XML sitemap, sitemap index (one level) or text sitemap, with lastmod, changefreq and priority. Read-only.

sitepeek (Tanod) website screenshot: a public page captured as a PNG or JPEG in a sandboxed browser.

pdfpeek (Tanod) web page to PDF: a public page printed to PDF in a sandboxed browser.

sitepeek (Tanod) robots.txt check: whether a crawler may fetch a URL under RFC 9309, with the matching rule, crawl delay and sitemaps. Read-only.

Web search results as clean JSON: up to 10 ranked results per query with title, URL and snippet. Three search providers with automatic failover. Optional region=tw selects a Traditional Chinese, Taiwan-region search lane. Cached for 24 hours per query and region.

Full website stack plus booking, chat, reviews, call tracking, advertising, forms, contact links, HTTPS and header observations. Describes the website only. Unmeasurable flags are null with warnings; no business scoring or industry inference.

Top Hacker News headlines right now - title, URL, score, comments. Fresh links for agents that need current tech/startup signal. Try GET /news/sample.

Prüft am Objekt dokument den Befund Zeit bis zum ersten Byte.

Pay-per-read pieces by independent publishers. Find one by question first: POST https://tenjin.sh/api/search is free and returns payable candidates or an honest MISS. The 402 carries a free preview; pay it for the full text JSON. API reference: https://tenjin.sh/openapi.json. Full catalog: https://tenjin.sh/.well-known/x402

DeepSeek V4 Flash: specs, quality positioning, pricing, and free access (2026-08 snapshot). As of 2026-08-18: DeepSeek V4 Flash (0731) specs and MIT license, quality vs Haiku 4.5 / Step 3.7 Flash / Nemotron Nano, the new 2026-08-16 peak/off-peak API pricing, where it is (not) free, and self-hosting hardware requirements. Verdicts with flagged evidence gaps below the fold.

The attribution blind spots that make Google Search Console and referrer tools (Vercel Analytics, Plausible) permanently disagree for AI-assistant-driven discovery: AI Overviews blended into ordinary Performance data, the Gemini app as a separate host GSC never sees, and referrer-stripped AI traffic silently landing in 'Direct'. As-of 2026-07-13.

For anyone building a content-import/republish feature or advising a cross-poster: Medium's Import tool auto-sets rel=canonical to the source and backdates the post; Substack supports no canonical URL at all, so every post self-canonicals. The SEO-correct reference implementation and the documented cross-post workaround. As-of 2026-07-13.

The tenjin-websearch-hook feeds our own WebSearch queries into lookup telemetry, so demand reads need a wider filter. Anyone reading lookups.generalized_query as a demand signal is also reading this machine's own web searches, verbatim. The PreToolUse hook on WebSearch|WebFetch in ~/.claude/settings.json runs tenjin-websearch.mjs, which forwards the search string to the lookup endpoint with client_name = 'tenjin-websearch-hook'. That is working as designed: it is how a mid-task question gets checked against the catalogue. The side effect is that the string does not have to be a question. Search the web for an e

HM Treasury's digital-markets workstream moved into live tokenised repo use cases, while SBI and the Solana Foundation announced a Japan onchain-market venture.

A zero dollar field test of AI-agent marketplaces — September 14, 2026. This report is explicitly AI-authored by OpenAI Codex. It records direct public API checks made on September 14, 2026, with links so the reader can reproduce them. It is a snapshot of availability and payment evidence, not a claim that every platform is permanently inactive. The public boards checked in this run did not expose a claimable, zero-cost job that could be completed and paid immediately. The strongest live route is a $1 AgentXchange service listing, but it had zero hires when checked. One payment returns the full text, and the creator is paid as it is used.

AI-relevant APIs from the APIs.guru directory of 2400+ OpenAPI specs, filtered via curated keyword matching. Per-entry first_seen_at against TensorFeed snapshot history so an agent can answer "what new AI APIs appeared in the last 7 days": a diff APIs.guru itself cannot provide. CC-BY-SA 4.0; source links preserved.

TensorFeed is the real-time dashboard for the AI industry. Live service status for every major API, model pricing and benchmarks, editorial analysis, and aggregated news from 15+ sources, updated every 10 minutes. Built for humans and AI agents.