Deep research report: plans several searches, reads up to 8 sources and writes a structured Markdown report (summary, key findings, details, open questions, numbered sources) with inline citations. Takes 20 to 60 seconds.

Current library docs for agents with stale training: the latest version of an npm or PyPI package, how to use it now, and the breaking changes since the version you know, from its README and changelog.

Answer grader: scores a draft answer 0-10 against the question, a rubric and/or source URLs, lists factual errors and unsupported claims with fixes, and returns an improved answer. A self-check before an agent ships. Also callable as GET with the same fields as query parameters.

Bulk reader: up to 20 web pages read and cleaned to text in one call (instead of 20 separate calls), each trimmed to your character limit. Unreadable pages are flagged, not failed. Also callable as GET with the same fields as query parameters.

Official US energy price forecast (EIA Short-Term Energy Outlook): monthly gasoline, diesel, WTI and Brent crude, Henry Hub natural gas and residential electricity prices for the next 12-24 months, with the latest actual and the 12-month change.

This week's gasoline or diesel prices across the US: national average, PADD regions, 9 states and 10 metro areas (Los Angeles, San Francisco, Seattle, New York, Chicago, Houston, Miami...), ranked with weekly change.

Electricity prices for every US state for the latest month (residential, commercial, industrial or all sectors) in cents per kWh, ranked cheapest first with 12-month change and the US average.

How many businesses of a kind are in a US county, state or ZIP: establishments, employees, annual payroll and average pay by industry (keyword or NAICS code), plus businesses per 10,000 residents for market sizing and competition checks.

Cited answers: ask a question, get a concise answer written from live web pages with numbered [n] citations and the source list. Searches the web, reads the top pages and writes only from what they say (gpt-oss-120b).

Ready-to-search chunks: turns a URL (page, PDF, Office file) or text into clean overlapping chunks with character offsets and bge-m3 embeddings (1024 dims) in one call, ready for any vector store. Up to 300 chunks. Also callable as GET with the same fields as query parameters.

Second opinion: three different AI models (gpt-oss-120b, Llama 3.3 70B, Gemma 4) answer independently, then you get the consensus, the points they disagree on, a confidence level and a combined best answer. Also callable as GET with the same fields as query parameters.

OpenAI-compatible chat completions on DeepSeek V4 Pro, a top open frontier model with reasoning, tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agents.citiviewgroup.com/v1/deepseek-pro and pay per token with x402 instead of an API key: $2.64 per million input and $7.92 per million output tokens, minimum $0.002 a call, at most $0.2158. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shap

Wallet activity alerts: watch any wallet on Base, Ethereum, Arbitrum, Optimism or Polygon for 7 days; every incoming or outgoing transfer (ETH, tokens, NFTs) is POSTed to your webhook URL within about 10 minutes. Check status with the watch id. Also callable as GET with the same fields as query parameters.

US imports and exports from official Census trade data: by product (HS code) the top partner countries with value, share and year-to-date; by country the trade balance and top products; or US totals, for the latest month or any month.

OpenAI-compatible chat completions on Zhipu GLM-5.3, frontier reasoning with tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agents.citiviewgroup.com/v1/glm5 and pay per token with x402 instead of an API key: $2.8 per million input and $8.8 per million output tokens, minimum $0.002 a call, at most $0.2322. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, rea

Rent a real Chrome browser for up to 60 minutes: opens a live session (optionally at a URL) and returns a session id, a screenshot, the page text and the clickable controls. Drive it step by step with /v1/browser/act (click, type, press, scroll, select, go back). The session stays open 10 minutes after each action. Also callable as GET with the same fields as query parameters.

Premium transcription with Deepgram Nova-3: smart punctuation and formatting, language detection, optional speaker labels (diarization) and word timestamps, for a public audio or video file. $0.012 per audio minute (set max_minutes), minimum $0.02. Add store=true (+$0.001) to get a 7-day share link instead of the data inline.

Premium image generation: FLUX.2 dev (highest quality), FLUX.2 klein 9B or 4B (fast), Leonardo Lucid Origin (photoreal, good text in images) or Leonardo Phoenix. Up to 1536 px per side. Priced per image by model, size and steps (about $0.006 to $0.08). Add store=true (+$0.001) to get a 7-day share link instead of the data inline.

The current US stock-market Fear & Greed index (0–100, CNN-style) with its sentiment rating and all five weighted components — volatility, momentum, put/call, safe-haven demand, junk-bond demand — each with value, weight, and reading. Includes the last 30 days of scores and a backtest of S&P 500 forward returns by sentiment zone. A one-call read of market mood. From x402stock

Ask any website or documentation a question: the site is crawled (up to 50 pages), indexed for 7 days and searched; the answer cites the pages it used. Later questions about the same site reuse the index. $0.03, or $0.05 above 25 pages.