Stock-market signals as a JSON API
Is this stock worth buying right now? Ask the API.
Give it a US stock or ETF ticker and get back a computed answer: where the stock is in its trend cycle, whether its chart just broke out, whether insiders are buying, and whether the wider market is in a risk-on or risk-off mood — fused into one 0–100 score with the reasoning written out. Built for people who write trading bots, research tools and AI agents, not for reading charts by hand.
What it answers
"Should I be accumulating NVDA?"
GET /v1/verdict/NVDA returns a score, a verdict of accumulate, hold, distribute or avoid, the factors behind it, and a sentence you can quote.
"Which of my watchlist is in an uptrend?"
GET /v1/signals/stage?tickers=AAPL,MSFT,AMD puts each ticker in one of four trend stages: basing, advancing, topping or declining.
"Is it a good time to be in stocks at all?"
GET /v1/macro reads credit spreads, rates, the dollar and futures positioning into a risk-on, neutral or risk-off regime. /v1/sector-breadth shows how many stocks in each sector are on buy signals.
"Are executives buying their own shares?"
GET /v1/filings/TSLA lists insider buys and sells from SEC Form 4 filings, with role, size and price, plus recent 8-K events.
"Tell me the moment something changes."
Webhooks fire when a ticker changes trend stage, a chart signal flips, the macro regime shifts, or insiders cluster — signed deliveries with retries.
"Would this rule have worked in the past?"
/v1/signals/stage/history gives up to ten years of weekly trend stages, computed only from data that was available each week, so backtests don't cheat.
How it works
1. Public and licensed data in
End-of-day prices for US stocks and ETFs, macro series from the Federal Reserve (FRED), futures positioning from the CFTC, and insider and company filings from SEC EDGAR.
2. Established methods applied mechanically
Four-stage trend analysis on a 30-week moving average, Point & Figure charting for breakouts and relative strength, bullish-percent breadth by sector, and a transparent point system for the macro regime. Nothing is a black box; every signal ships with its rationale.
3. One JSON answer out
Each response says what it is based on (as_of), how fresh it is, and when to ask again, so a bot or an AI agent knows how much to trust it. Signals refresh on a daily and weekly cadence; this is not a real-time quote feed.
Who it's for
Developers building trading bots
Skip months of building your own trend, breadth and filings pipelines. Call an endpoint, get a decision-ready signal, keep your logic focused on sizing and execution.
AI agents and assistants
A hosted MCP endpoint at /mcp works with Claude.ai connectors, ChatGPT and any client that takes a URL, with nothing to install; the same tools ship as an open-source package (uvx vanoe-intelligence-mcp) for Claude Desktop and Claude Code. Each call is metered against your own key — nothing hidden.
Researchers and quant hobbyists
Backtest-safe stage history, honest billing (only successful answers cost credits, unknown tickers and outages are free), and structured errors with a request id when something goes wrong.
Pricing
One credit per signal per ticker. The composite verdict and the historical stage series cost 5 credits per call. Paid plans keep working past the included credits and bill the excess per credit at month end; the Free plan stops at its allowance.
Free / Dev
- 1,000 credits a month
- 2 requests per second
- Hard cap — upgrade to keep going
- No webhooks
- All signals, MCP server, API reference
Starter
- 10,000 credits a month
- 5 requests per second
- Overage $1.20 per 1,000 credits
- No webhooks
- All signals, MCP server, API reference
Pro
- 50,000 credits a month
- 10 requests per second
- Overage $1.00 per 1,000 credits
- Webhooks included
- All signals, MCP server, API reference
Business
- 500,000 credits a month
- 50 requests per second
- Overage $0.80 per 1,000 credits
- Webhooks included
- All signals, MCP server, API reference
Prices in USD, billed by Stripe. Change or cancel any time from the customer portal (POST /v1/billing/portal). Paid plans start on the Free tier and upgrade in one click from the signup page or via POST /v1/billing/checkout.
Quick start
# 1. Get a key at https://api.vanoe.ai/signup, then:
curl -H "Authorization: Bearer sk_live_…" \
"https://api.vanoe.ai/v1/verdict/AAPL"
# → {"data": {"ticker": "AAPL", "score": 70.6, "verdict": "accumulate",
# "confidence": 0.74, "rationale": "Stage 2 advance …", …},
# "as_of": "2026-09-08", "freshness": "end_of_day",
# "suggested_recheck_seconds": 86400, "request_id": "…"}
# Several tickers in one call (1 credit each):
curl -H "Authorization: Bearer sk_live_…" \
"https://api.vanoe.ai/v1/signals/stage?tickers=AAPL,MSFT,NVDA"
# What you've used this period:
curl -H "Authorization: Bearer sk_live_…" "https://api.vanoe.ai/v1/usage"Full reference with every endpoint, parameter and error code at /docs. Errors are structured with stable codes and a request_id; rate limits return 429 with Retry-After.
What it is not
It is not investment advice, a broker, or a real-time quote feed, and it does not know your portfolio or risk tolerance. It computes well-known technical and fundamental signals from public and licensed data and reports them with their reasoning; what you do with them is your decision. Signals can be wrong, late or unavailable. See the terms.