Getting started
The Public Signals API gives you live prediction-market contest snapshots and Cotes AI signals over HTTPS JSON and Server-Sent Events.
It serves the same signals SpectralBot shows in the web app, for Kalshi’s bitcoin 15-minute markets (series KXBTC15M). A contest is one 15-minute market. While it’s open, the model re-reads it every few seconds and raises signals, each with a side (up or down), a calibrated confidence, the venue’s entry price, and an edge estimate. When the market settles, every signal is graded against the result.
What you can build
Section titled “What you can build”- Dashboards and alerts: stream new signals as they’re raised and filter on your own confidence or edge thresholds.
- Research: pull settled history, with every signal already graded, to measure how the signals perform under your own rules.
- Bots and agents: feed the signal into your own decision logic. The API publishes signals only; it never places orders.
Access uses an API key tied to your Cotes account, and works while your trial or subscription is live. There’s no first-party SDK: call HTTPS and JSON directly from any language.
Base URL
Section titled “Base URL”https://api.cotes.aiQuick start
Section titled “Quick start”export COTES_API_KEY='your-key'export BASE='https://api.cotes.ai'
# Liveness (no auth)curl -sS "$BASE/v1/health"
# Active contest for a seriescurl -sS -H "Authorization: Bearer $COTES_API_KEY" \ "$BASE/v1/contests/active?series=KXBTC15M"Endpoints
Section titled “Endpoints”| Method | Path | Auth |
|---|---|---|
GET |
/v1/health |
none |
GET |
/v1/contests/active?series={series} |
API key |
GET |
/v1/contests?series={series} |
API key |
GET |
/v1/contests/{ticker} |
API key |
GET |
/v1/stream/contests?series={series} |
API key (SSE) |
series is a series prefix such as KXBTC15M. Use the full ticker only on /v1/contests/{ticker}.
Next steps
Section titled “Next steps”- Authentication — API keys
- Contests & signals — response shapes
- Streaming (SSE) — live updates
- Rate limits — throttling and
429handling - Agent prompts — sample prompts for coding agents
- API reference — OpenAPI reference
llms.txt— curated index for LLMs