GET /labs/liquidation-map?symbol=BTCUSDT&range=24h GET /labs/liquidation-map/stream POST /labs/liquidation-map
Exposure density by price and time with old positions fading; levels with age, 4h change, expected closes if crossed and touch probability within 1h, 4h and 24h; the probability that the long or short side is reached first.
POST /labs/monte-carlo {symbol, source: "arcdelta", horizon_steps, paths, levels}
GET /labs/calibration?symbol=BTCUSDTPrice fan, terminal distribution, touch and close-beyond probabilities for levels, maximum run-up and drawdown, indicator distributions.
POST /labs/risk/var {symbol, side, notional, horizons, confidence, loss_budget}VaR and expected shortfall at the close and at the worst point inside the horizon, the probability of breaching the budget, and a PnL histogram.
POST /labs/risk/liquidation {symbol, side, entry, leverage, maintenance_margin, closing_fee, stop, horizons}Liquidation price, probability of reaching it within 1h to 7d, stop-touch probability and the largest leverage with under 1% and 5% liquidation risk.
POST /labs/trade-plan {symbol, side, entry, stop, take, horizon}
GET /labs/trade-plan/calibration?symbol=BTCUSDTProbabilities of take first, stop first and neither, expected R after fees, the break-even hit rate, fill probability for pending entries, R quantiles and a grid of takes from 0.5R to 5R.
GET /labs/volatility?symbol=BTCUSDT
HAR forecast with a 10–90% band for 1h, 4h and 24h next to the GARCH of the Monte Carlo engine, the last week's QLIKE check, at-the-money IV at 1 and 7 days and its spread to the forecast and to realised volatility.
GET /labs/correlations?window=3d&resolution=1h&symbol=SOLUSDT
Correlation matrix ordered by cluster, beta to BTC with its error, betas on up, down and stressed BTC bars, volatility net of BTC, clusters and a rolling 24h beta for one coin.
GET /labs/seasonality?symbol=BTCUSDT
Return, volatility and turnover by UTC hour and weekday with 95% intervals, the share of up hours against the base rate, and which effects survive the multiple-testing correction.
GET /labs/hawkes?symbol=BTCUSDT&exchange=binance
Branching ratio n (total, buy to buy, buy to sell), memory half-life, current intensity against the baseline, expected trades over 10 s to 5 min, and the fit check: time-change residuals with a KS test and QQ plot, out-of-sample likelihood against Poisson, and trades per 2 s against Hawkes and Poisson.
GET /labs/hawkes/market-maker?symbol=BTCUSDT&exchange=binance&minutes=10
For each quote offset: fills per minute, PnL split into spread captured, adverse selection (5 s markout) and inventory effect, spread of outcomes and the 5% worst case; calm against stressed flow.
GET /labs/funding-carry?symbol=BTCUSDT&side=long¬ional=10000
Forecast of the next-day average rate, annualised rate on the venue's own interval, carry per day and at the next settlement, venue that pays best, live check against the last rate.
GET /labs/execution-cost?symbol=BTCUSDT¬ional=100000
Spread, slippage curve from $1k to $1M, median and stressed (p90) cost, taker fee and round-trip cost per venue, best venue.
POST /labs/backtest/check {returns, periods_per_year, trials, variants}Sharpe with a bootstrap interval, Probabilistic and Deflated Sharpe, minimum track record, drawdown at 95%, probability of backtest overfitting.
GET /api/v1/labs/access GET /api/v1/labs/calibration?symbol=BTCUSDT Authorization: Bearer <session-token> X-API-Key: <account-api-key>
Monte Carlo also accepts client data: closes, timestamps, highs, lows (5m). Without timestamps the previous 0.5 bootstrap is used.
Outputs describe distributions, probabilities and costs. They are not trading recommendations.