Explore APIs

Generate a captioned meme image. Pay per request in USDC on Base mainnet.

Upload an image with payment and get a public URL. Accepts multipart form-data (field 'image') or JSON {"file": "<base64>"}. 10MB max, permanent hosting (no expiration). PNG, JPEG, GIF, WebP.

Remove the background from an image URL and return a hosted transparent PNG URL. Paid responses include a feedback_id. Please rate the result for other agents with one free GET: https://clearcut.clawca.sh/feedback/rate?feedback_id=FEEDBACK_ID&outcome=fully|partially|no.

Buy $0.10 of prepaid credits for the YiduoChan inference gateway and receive a working API key in the response. The key works with any OpenAI-compatible client against https://yiduochan.com/v1 and covers chat, reasoning, text-to-speech, image and video models. Credits are spent per token at published rates; no account, email or signup is required.

Fetch / scrape a URL and read any public web page as clean, LLM-ready Markdown: main text without navigation, ads or footers, plus title, author, date, site name and language. Respects robots exclusion rules and the noai opt-out; max_chars caps the output (default 20000). Static HTML only (no JS rendering).

Use when you need a short, sourced explanation of a topic, place, organization, product or concept: returns the Wikipedia article's lead section as plain text plus title, short description, thumbnail and original image, page URL, Wikidata ID and last-modified time, in any Wikipedia language (redirects followed). Every response carries the CC BY-SA 4.0 license, credit line and source link required

Use this when a question needs several of these tools chained together and a written answer, for example comparing tokens or researching a launcher. Price: $0.541 in USDC on Base, or $0.550862 in USDG or $SWOGE on Robinhood Chain (tool price + settlement cost, minimum $0.02).

agentic.no inference: OpenAI-compatible audio transcription (POST /v1/audio/transcriptions)

Service: Tripadvisor (https://tripadvisor.x402.paysponge.com/api/v1/location/:locationId/photos)

Find transcript passages matching a phrase or terms in a public YouTube video, with timestamp citations.

Fetch a web page and return it as clean markdown a model can read — the words, the headings and the links, without the navigation, scripts or cookie banners. Send `render: true` for pages that only appear after JavaScript runs. $0.0050 per page, flat. No account, no API key, no signup: the payment IS the authentication.

Current Base gas in one call: the live gas price, the current base fee, the base-fee range across the last 20 blocks, whether fees are rising, falling, or flat, and a cheap-window hint drawn from that data. Use this when an agent wants to time a transaction instead of paying whatever the moment charges.

Render any public web page in headless Chrome and return it as an A4 PDF (base64 JSON, or raw PDF with ?raw=1). Use when an agent needs a printable/archivable copy of a web page, a receipt or an article to store, attach or send.

Reader Pro: fetch a public web page and return structured data, no LLM: OpenGraph/meta tags, parsed JSON-LD (schema.org), HTML tables as row objects, deduped internal/external links, emails/phones/social profiles, heading outline, images with alt text, plus optional CSS-selector fields.

Use for current events, monitoring a company/person/topic in the press, finding recent coverage before answering, or building news digests. Returns up to 20 articles with title, direct article url (no redirect wrapper), publisher, published time (ISO 8601), snippet and image when available. sort=date for newest first; freshness=hour|day|week|month to limit age; market for regional editions (en-US,

Use when you need to read one public web page: fetches the URL live and returns its main readable content as clean Markdown (or plain text), with navigation, ads, cookie banners and boilerplate removed, plus title, byline, publish date, language and word count. Respects robots.txt. Server-rendered HTML only (no JavaScript execution).

Extract text per page from a PDF (plus metadata) as JSON. Digital PDFs only, no OCR.

AI meeting notetaker comparison dataset: 13 commercial tools plus Microsoft Teams, Google Meet and Notion, compared on pricing (incl. hidden costs), Dutch/French support, speaker identification, export data quality, security certifications and EU/GDPR posture. Independent research by Machinegeist; no vendor affiliations, no commissions.

Verify an exact Circle USDC payment from a Base-mainnet transaction receipt and finalized chain evidence

Use when an agent must decide whether an address or x402 service has actually received USDC from anyone other than its operator - before paying it, listing it, or trusting a claim about it. Returns third-party total, distinct senders, first/last seen, block height. Scope: Base + USDC.

Same as the free /v1/extract but without the 30 requests per day limit: fetch one public static HTML or JSON page and return structured data (text, attr, list, table, price, events, page, links, json) as JSON, CSV or ICS. Honours robots.txt. No JavaScript rendering. Failed calls (4xx/5xx) are not settled.

Bulk extract domains from page: up to 20 urls in one call, processed concurrently, results in input order with a per-item error field and a failure count. Same answer per item as the single endpoint. Batch enrichment for agents that hold a list. $0.10 per batch.

Compress images to reduce file size with configurable quality. A photo compressed to quality 30 is typically 90-95% smaller with acceptable visual quality. Useful for reducing storage costs, optimizing web page load times, preparing image uploads, and bandwidth reduction for mobile users. Accepts PNG, JPEG, WebP, AVIF. Returns JPEG.

Convert URL, PDF, HTML, or image to structured Markdown (title, sections, word count)

Extract the readable article content from any url as clean markdown with a sha256.

Free audiobooks on "Americans": public-domain recordings (LibriVox and Internet Archive audio) whose subject tags match, with runtime, language and mp3 links, most downloaded first. Add words to narrow. $0.01 per page of 20.

Convert any web page URL to clean Markdown for LLMs and agents: fetches the page, removes navigation, ads, scripts and boilerplate, keeps the main article content with headings, lists, tables, links, images and code blocks, and returns title, meta description, word count, headings outline and outbound links. Web scraping, article extraction, readability and HTML-to-Markdown in one call, no API key

Returns the fields described by a JSON Schema from one public HTML page (no JavaScript rendering). Charged only when ok is true.

Agent cannot hear. Send audio, get text. It never leaves this Houston box. Whisper large-v3. $0.03 USDC.

Estimate exact token count (tiktoken-style) and trim text to a budget — $0.001 USDC/call on eip155:8453. Pay-per-call via x402 — no API key, no account. Free samples daily.