All projects on Base matching “text”

Full text of one section of the SSA Program Operations Manual System (POMS). Get the id from GET /search?q=<keywords> or GET /part/:code. Use this when you need the complete, verbatim text of a specific POMS section for a disability, retirement, SSI, or Medicare question, not a summary.

Extract text and tables from a Word .docx file ($0.005 USDC via x402). Input: a public https url to a .docx, or docx_base64. https only — http, file, data, localhost, and private IPs are rejected. Caps: 10 MB file, ~15s timeout, max 5 redirects. Tables appear as [table N] placeholders in text. Unicode dashes/minus signs normalized to '-'. Old binary .doc files are not supported. Returns JSON { fil

Finds every date, time, range and period in text and resolves each to an ISO 8601 value with UTC offset plus a start/end span in an IANA timezone, relative to a reference instant. Reports matched text, index, ambiguity flags and confidence.

Safe Read: fetch one public web page and get its clean main text, title, metadata, a sha256 content hash, and prompt-injection warnings with a 0-100 risk score (visible text, hidden elements, HTML comments, alt/meta attributes, invisible Unicode, base64). SSRF-guarded: DNS-checked and pinned public addresses only, 4 redirects max, 2 MB, 8 s, text/html and text/plain only. Errors are not charged.

Pay $0.05 USDC to seal up to 100 KB of text until a future date. Content is inaccessible via GET /open/{token} until unlock_at passes. An optional label is visible before unlock via GET /status/{token}. Max unlock date: 10 years from now. Network: Base Mainnet. Each request stores one sealed text capsule and returns a token for later retrieval.

Full text of one section of the IRS Internal Revenue Manual (IRM). Get the id from GET /search?q=<keywords> or GET /part/:number. Use this when you need the complete, verbatim text of a specific IRM section on IRS examination, collection, appeals, penalty, or disclosure procedure, not a summary.

Full text of one IRS Internal Revenue Bulletin document (Revenue Ruling, Revenue Procedure, Notice, Announcement, or Treasury Decision), 2003 to present. Get the id from GET /search?q=<keywords>. Use this when you need the complete, verbatim text of a specific IRS guidance document for tax research, not a summary.

Page to JSON: scrape and extract any public web page URL into clean structured data JSON. Web scraper / HTML-to-JSON extractor / readability parser for AI agents and LLMs: returns title, author, site name, published date, main article text (plain text), word count, up to 200 links and an optional short summary. Web scraping, content extraction, metadata extraction, article parsing, crawl, RAG inge

Analyze a block of text: character, word, sentence and paragraph counts, syllable count, average words per sentence, Flesch Reading Ease and Flesch-Kincaid grade scores, estimated reading and speaking times, and the top repeated words. Input: the text (up to 20000 characters). Errors are returned free (settlement is cancelled on failure).

Full-text metadata search across every arXiv preprint. Filter by free-text query, title, author(s), category (cs, math, stat, physics, q-bio, q-fin, econ, eess, etc.), and submitted-date range. Returns titles, authors, abstracts, primary category, DOI, journal-ref, abs URL and PDF URL. Sort by relevance, lastUpdatedDate, or submittedDate.

Text-to-structured-JSON extraction: POST plain text, receive emails, phone numbers, dates, monetary amounts and URLs as JSON.

SHA-256 hex digest of UTF-8 text. Body: { text: "..." }.

Search X/Twitter for any query and get the actual matching tweets — keyword, $CASHTAG, from:handle (a user timeline), @handle (mentions), or boolean OR. Each tweet returns author, full text (long-form note tweets included), timestamp, likes and retweets (reply/quote counts when available). Most-recent-first for real-time monitoring and alerting. Live X search backend, pay-per-call USDC, structured

Extract named fields from unstructured text into strict JSON. Use when an agent must turn an email, filing, invoice, or description into {field: value} records up to 4,000 characters.

Source-bounded fact-check. Verify a claim against provided source text. Returns verdict: supported, contradicted, or unverifiable. Does NOT search the web.

Compute a SHA-256, SHA-384, or SHA-512 digest of UTF-8 text; returns hexadecimal output (default SHA-256).

Jev Decision ($0.005/call): Ask Jev (TypeSafe System One) typed questions about one state and get numbers back, not text: noul answers the probability a yes/no is yes; choice picks an option with a probability for every option; score places the state on an ordered scale of levels with a probability for every level. Same body and answer as TypeSafe's POST /v1/systemone (model optional, state as tex

On-page SEO audit of one public page from its HTML only: title and description length, one H1, canonical link, language, viewport, robots meta, Open Graph tags, images without alt text, internal and external links, word count. Returns each check with its value and pass or fail. No Core Web Vitals, backlinks or keyword volumes.

Generate a video from a text prompt, or animate an image_url from its first frame. The paid response waits about as long as the model usually takes to render and returns the video URL, else a statusUrl to poll (Prefer: wait=N sets the wait). 8 models including Google Veo 3.1, Kling 3.0, Seedance 2.5, Wan 2.7 and MiniMax Hailuo 3, 4 to 15 seconds, 16:9 or 9:16, from $0.42. GET this URL for every mo

AI IMAGE GENERATION — POST {prompt} and get back a PNG, base64 in JSON (?raw=1 for raw bytes). Gemini 2.5 Flash Image (nano-banana): photoreal scenes, illustrations, product shots, UI mockups — renders text in images well. Optional {aspect_ratio}: 1:1 (default), 16:9, 9:16, 4:3 + 6 more. Reference images: pass {url} or {image_base64}, or up to 3 in {reference_images}, to edit, restyle, or compose

Cheapest real end-to-end test of your pay-per-call (HTTP 402) client: pay US$0.002, get back what was paid (payer, amount, network, timestamp) and the text you sent; the settlement receipt is in the PAYMENT-RESPONSE header. A free trial call returns paid_usd 0. Use it to check a wallet, a client library or a facilitator before buying something bigger.

Unblocker for AI agents: send {url} and get the page back as clean Markdown, with title, description, language, final URL and HTTP status. Gets through Cloudflare and other common bot protection and can render JavaScript-heavy pages. Set format to html or text for those instead. A page that can't be fetched (blocked, error status or empty) is not charged. No API key, proxy or account: pay per call

Generate an image from a text prompt

Text-to-image generation on Venice models (Flux, SD3.5, GPT-Image, HunyuanImage, and more), paid per request in USDC on Base via x402, no API key. Charge is catalog unit × variants (1–4). A bare unpaid probe (no model) quotes default venice-sd35 (from $0.01; flux-2-pro $0.015). S

Headless scraper proxy for AI agents at $0.01 per accepted scrape. Fetch a public HTTPS URL and return clean LLM-ready Markdown. Agent-safety guarantee: output is validated as clean text before serving; binary or garbled content is rejected with no charge.

Scrapes any webpage and pulls title, description, canonical URL, OpenGraph + Twitter card metadata, headings, and outbound links from a single URL. Server-side rendering; body content rendered as text, raw HTML, or clean markdown, with optional link extraction. Cheerio-based with no headless browser, so it is fast and cheap, ideal for static pages and SSR sites. For JS-heavy SPAs that need a real

Fact-check numbers in Korean finance text: every checkable number (rates, KTB yields, FX, listed-company revenue and profit, % vs %p, 조/억/만 units) marked MATCH or MISMATCH against the official value with date and source (ECOS, KEXIM, DART). Numbers with no source stay unverified.

Headless scraper proxy for AI agents at $0.01 per accepted scrape. Fetch a public HTTPS URL and return clean LLM-ready Markdown. Agent-safety guarantee: output is validated as clean text before serving; binary or garbled content is rejected with no charge.

Search the web and read the top pages in ONE call: 10 results (title, url, snippet, date) plus the clean text of the best pages, with fetch time and sha256. French and Canada by default when the query is French; official-sources mode (governments, registries, courts, laws); freshness filter; site: restriction. No results = HTTP 404 = you are not charged. Input: query, optional read (0-5), official

GPT Image 2.5 Sunburst Medium - GPT Image 2.5 Sunburst, medium quality: text to picture. Precise: every detail lands where you ask. Any shape up to 3:1, transparent PNG or JPEG. $0.015, about 25 s.