Apify — Tweets by search term, handle, or conversation.

Company firmographics by domain via Apollo (works on the current plan): name, employee count, industry, socials, and often a COMPANY PHONE number. Pass { domain: 'stripe.com' }. Good for grounding a draft in company facts when the lead's company is thin.

Step 2 of video assembly. Create a CueFrame project for any video style (1A demo, 1B PIP-avatar, 1C conceptual, 1D launch). Returns a project_id used by put_composition + render. Params: name (required), format {aspectRatio 16:9|9:16|1:1|4:5, fps 24|30|60, resolution hd|fhd|4k}, optional width/height/brandKitId.

Exa — retrieve content for URLs or document IDs via our API key. Charges 0.1¢ per (url or id) × content field requested.

Exa — semantic web search via our API key. numResults up to 100. For people/lead discovery set category:"people" with an open ICP query.

Generate or edit images, video, music, and speech via fal.ai. Pass `model` (one of the registered keys) plus the model-specific params (prompt, image_url, aspect_ratio, duration, text, etc.).

Stage a media file on the fal CDN before a fal generation. Returns { upload_url, file_url }: PUT the raw file bytes to upload_url (with the matching Content-Type header), then pass file_url as the image_url/video_url/audio_url param of the generation. Upload originals UNCOMPRESSED — never downscale or re-encode; high-res inputs cost nothing extra and compression degrades outputs.

Store a file from the local machine in your persistent Vaaya file library. Returns put_url (PUT the raw bytes there with curl) plus file_id and get_url. Files persist across tasks — check files/list before re-uploading. Max 100MB per file.

Fetch a file from a public URL into your persistent Vaaya file library (server-side — no local download needed). Returns file_id and get_url. Max 100MB per file.

Firecrawl — Crawl a website starting from a URL, following links.

Firecrawl — Extract structured data from URLs using a schema.

Firecrawl — Map all URLs on a website without scraping content.

Firecrawl — Scrape a single URL and return clean markdown/HTML.

Firecrawl — Search the web and return scraped results.

Modal — Create a sandboxed compute environment (CPU by default, 300s timeout). Pass `gpu` (T4 | L4 | A10G | A100 | H100) for GPU workloads like model inference.

Modal — Run a command in a running sandbox and return its output.

Modal — Terminate a running sandbox.

Parallel — AI-powered web search via x402 (1¢ flat).

Parallel — Start an async AI research task. Pricing depends on `processor`: pro 10¢, ultra 30¢. Returns { run_id }; poll task-status until completed.

Reveal a person's verified email via Prospeo. Pass `person_id` (from search-people) or `linkedin_url`. Returns the unmasked verified email. 1 credit; free if the record was enriched within 90 days.

Vaaya — one paid endpoint for agents. Describe any goal in plain English and get back the exact Vaaya calls to run: image & video generation, product-demo videos, web search & scraping, deep & market research, GTM lead enrichment & outreach, code sandboxes, browser automation, email, and persistent memory. Returns ready-to-run { service, action, params } calls with prices — then POST each to /api/run/{service}/{action}. Pay-per-call in USDC on Base (x402), no account or API key.