Paid services on Base matching “cheap”

Cheap robots.txt preflight check before you call the Minifetch /extract and /run/seo-page-audit endpoints: returns whether Minifetch may fetch a target URL (allow/deny) plus its crawl-delay. If blocked and the site is not yours try our external proxy routes. If blocked and the site is yours or to set a custom crawl-delay read https://minifetch.com/tutorials/unblock-minifetch Checks the URL as give

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

Live crypto prices: USD spot for BTC, ETH and SOL in one call, fetched per call (not cached), so the figure is the number right now. A cheap, high-frequency data lane for x402 buyers budgeting in the unit they pay with. Sourced from public feeds (Coingecko primary, Kraken fallback).

A lightweight, verifiable web search proxy that accepts a natural-language query and returns ranked, cited results. It is designed for agent-to-agent and x402-metered traffic: one paid call yields one clean search response with title, URL, snippet, and a stable rank. Use it when your agent needs cheap, low-latency public web search without managing multiple upstream providers. Requests are validat

Metalift scrape: URL → LLM-ready markdown with WAF/retail escalation, JS render, and residential proxy when needed. Use instead of a plain HTTP fetch when Cloudflare, bot checks, or SPAs block cheap scrapers. Also works for static pages (pay only for the path used). (5 credits ≈ $0.005 USDC)

Cheap pre-purchase recall screen, lite version of buy-check for agents with small per-call budgets. For shopping and buyer agents: one call returns the official CPSC recall screen (government rows verbatim) and a deterministic recall-only verdict, plus a pointer to the full $0.50 buy-check for timing, alternatives, and trust flags.

Summarize text. Classify sentiment. Rewrite. Extract keywords. Translate. When to use: cheap agent glue / probe steps for buyer-supplied text. Returns JSON for $0.01 per call in USDC on Base via x402. No API key. Local-fast NLP; no login scrape. Success JSON includes next_tasks hints for same-session follow-ups.

Search Obelisk's curated spy ad catalog when you need competitor creative examples by keyword, brand, or platform. Returns JSON ad cards. Use limit=1 for a cheap first call.

Detect whether an arbitrage opportunity exists in a set of token exchange rates (multi-pool negative-cycle scan). Cheap boolean + magnitude signal for trading agents. POST a swap-rate graph, get back whether a profitable cycle exists and how large — without the path.

What token is this? Read a Base token's name, symbol, decimals and total supply in one cheap typed call, with block-level freshness and explicit limitations. Identity is shared across agents for 7 days while total supply is re-read on every call beyond the block window the answer was quoted for. Positive-sum by design: $0.03 cold, $0.02 when the token identity is already shared, $0.01 on a shared

Fast, cheap spam-risk gate for one email: pass/warn/fail, a 0-100 score, and up to 3 flagged phrases. Use for a go/no-go before sending or for bulk screening of many drafts. No rewrites. For a full audit with reasons, subject-line risk, and rewritten copy, use analyze-email-deliverability. Content signals only; no inbox-placement guarantee.

Cheap generic EVM reads on Base for AI agents: native balance, nonce, contract code, ERC-20 token balance, eth_call, gas price, latest block, and transaction/receipt lookups. One call, read-only, $0.001.

Cheap web search for AI agents: give it a query, get up to 10 live web results back as JSON (rank, title, url, domain, snippet). Optional region (e.g. us-en) and safe-search level. Sources tried in order: DuckDuckGo, Bing, Yahoo. Results link to the live web; pair with a /read service to fetch the pages.

Prediction-market divergence feed: the same event priced differently on Kalshi vs Polymarket. Returns matched events whose last prices differ by at least min_gap_pp points, with both venues bid/ask, the last-price gap and the executable gap (rich venue bid minus cheap venue ask), and a match-confidence score. The benchmark is the other venue price for the same event; matches are heuristic, so chec

AI Web Extractor — turn ANY url into clean, LLM-ready markdown. POST {url}; get the main content as markdown (boilerplate/nav/ads stripped) with title, description, and links. The scrape / read / url-to-markdown primitive for RAG and research agents. Fast, cheap, x402-native.

Cheap Solara tip for agents — small paid sanity check / discovery plumbing.

Live Base snapshot for AI agents. Each GET returns the current Base block number, base fee, gas price, ETH-USD price, and a unique receipt. Price is exactly $0.01 USDC on Base via x402. No API key and no RPC method. GET /ping returns the same snapshot. Use it as a chain read or as the cheap call that proves an x402 client can pay.

Cheap x402 ping. Returns server time and receive wallet. $0.001 USDC on Base.

OpenAI-compatible LLM inference and chat completions via discounted Venice API credits. Pay USDC to receive a live Venice.ai API key for /api/v1 models, chat, images, audio, video, and embeddings. Same-Day credits are 30–90% below Venice direct and expire at 23:59 UTC; Prepaid API Keys support recurring agent jobs.

Ask a live crypto, stock, or macro analyst desk any market question — social sentiment, dominant narrative, Polymarket & Kalshi prediction-market odds, sentiment-vs-price divergence, whale positioning and funding context — answered fresh in 10-180s. ?q= free-form and/or ?asset=BTC. A live specialist desk at generic-AI-research prices. No charge if the desk fails to answer. Descriptive research, no

OpenAI-compatible chat completions for hundreds of open and closed models (DeepSeek, Kimi, GLM, Qwen, Llama, Claude, GPT, Gemini) through one endpoint, each call routed to the cheapest healthy provider for that model. Pay per call in USDC on Base with no API key or account: the 402 quotes this prompt plus max_tokens (up to 4,096). Streaming and tool calls supported. Model ids and prices: https://a