web-search-and-content

Juniper Agent Web Intelligence: one Brave web search, fetch up to three public HTTPS pages and extract source-backed JSON (title, metadata, headings, text, links, JSON-LD). 0.01 USDC on Base per request; no signup. HTML/text/JSON only; no JavaScript rendering or arbitrary LLM schema. Reuse your private request_id on pending responses.

Web search that reads the results: give a query, get the top web results plus the full text of the top 1-3 pages, each read in a real browser. For research, RAG and fresh answers in one call.

Extract every HTML table from a page (or raw HTML) as structured JSON: headers and rows kept intact. The deterministic answer to 'get the pricing table / comparison table / stats table from this page' — no vision model needed. Use this when an agent needs to hTML tables → structured JSON rows and columns.

SingIt Ask: one answer from deepseek-v4.1-flash, OpenAI-compatible. Paid per answer; charged only when the answer came back.

Exa Neural Web Search: Search the web using Exa through BlockRun and return up to five ranked source records. Includes provider identity and retrieval time. Query is sent to Exa via BlockRun. Results may omit snippets or dates; no locale, engine selection or completeness guarantee. 0.04 USDC includes up to five Exa results.

Figure captions — Structured extraction: Structured extraction for Figure captions. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded structured extraction result.

Public Website Crawl to Markdown: Crawl up to five public HTTPS HTML pages on one origin, following links to depth two. Returns basic markdown, titles, links and skipped-page reasons. Observes robots.txt and crawl delays. Static pages only; 35-second and 8 MB limits. Partial results are identified. 0.01 USDC includes up to 5 static pages on one origin.

Level-four headings — Attribute extraction: Attribute extraction for Level-four headings. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded attribute extraction result.

Articles — Structured extraction: Structured extraction for Articles. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded structured extraction result.

Unordered lists — Attribute extraction: Attribute extraction for Unordered lists. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded attribute extraction result.

Image alternative text — HTML fragment extraction: HTML fragment extraction for Image alternative text. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded html fragment extraction result.

Unordered lists — Structured extraction: Structured extraction for Unordered lists. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded structured extraction result.

Description metadata — Attribute extraction: Attribute extraction for Description metadata. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded attribute extraction result.

Button labels — Structured extraction: Structured extraction for Button labels. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded structured extraction result.

Image alternative text — Joined text extraction: Joined text extraction for Image alternative text. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded joined text extraction result.

Disclosure summaries — Joined text extraction: Joined text extraction for Disclosure summaries. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded joined text extraction result.

Option labels — Attribute extraction: Attribute extraction for Option labels. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded attribute extraction result.

Image alternative text — Distinct value extraction: Distinct value extraction for Image alternative text. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded distinct value extraction result.

Description metadata — Joined text extraction: Joined text extraction for Description metadata. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded joined text extraction result.

List items — Attribute extraction: Attribute extraction for List items. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded attribute extraction result.

Strong-emphasis text — Structured extraction: Structured extraction for Strong-emphasis text. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded structured extraction result.

Main content — HTML fragment extraction: HTML fragment extraction for Main content. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded html fragment extraction result.

Page header blocks — Structured extraction: Structured extraction for Page header blocks. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded structured extraction result.

Disclosure summaries — Attribute extraction: Attribute extraction for Disclosure summaries. One public HTTPS page or supplied HTML; static parsing, no JavaScript rendering, login or access bypass. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one bounded attribute extraction result.