We're building the most comprehensive crypto data API we can, and it's still growing — there's always a coin, a field or an endpoint we haven't got to yet.
Please tell us about any data you think Crypto Data API should nail but doesn't. We're data nerds who love to geek out about market data, trading bots, AI agents, or how to make your trading stack work in general. Prefer a form? Send feedback.
Per-coin regime probabilities for all Hyperliquid perps, every 15 minutes — Pro.
See pricing →
Crypto Quant Regimes
Our quant regime-probability engine — a Hidden Markov Model (HMM) trained on years of hourly market data — classifies the whole market and every Hyperliquid crypto perp into one of 6 short-term regimes, with calibrated probabilities for direction, volatility and liquidation risk, refreshed every 15 minutes. Nothing is a black box: every number ships with the features, posteriors and calibration that produced it.
Current Market Probabilities
Range / Low Volatilitywhole-market regime · in regime 6h
Model confidence
59%
in its regime call
Chance of a vol spike (24h)
2%
from 1,000 simulations
Chance of a >5% drop (24h)
5%
from 1,000 simulations
Where will the market be in 24 hours? — probability across five outcomes, left = falls, right = rises
10%Strong fall
22%Mild fall
33%Sideways
24%Mild rise
11%Strong rise
▼ MARKET FALLSMARKET RISES ▲
Tomorrow's likely range — 1,000 simulations of the next 24 hours
Worst likely
-4.4%
only 5% of runs end lower
Most likely
+0.1%
the median outcome
Best likely
+4.4%
only 5% of runs end higher
median +0.1%
-4%-2%0+2%+4%
Simulations are balanced: half of the 1,000 runs finish between -1.6% and +1.8%. The wide band covers 90% of simulated outcomes, the bright band the middle 50%; the marker is the median.
The 6 regimes
Every market hour gets sorted into one of these six states. Each implies a different way to trade — or not trade.
Strong Trend (Bull)
Sustained directional move up, positive funding, OI expanding.
Playbook: Trend-following ON, mean-reversion OFF
Whole market: 21% of the time since 2019, typically lasting ~3 days at a stretch.
Strong Trend (Bear)
Sustained downtrend, negative funding, OI expanding on the short side.
Playbook: Short trend ON, long momentum OFF
Whole market: 13% of the time since 2019, typically lasting ~2 days at a stretch.
Range / Low Volatility
Low ATR, choppy funding, tight OI range.
Playbook: Mean-reversion ON, trend OFF
Whole market: 27% of the time since 2019, typically lasting ~2 days at a stretch.
Choppy High Volatility
High ATR, no clear direction, elevated liquidations.
Whole market: 8% of the time since 2019, typically lasting ~3 days at a stretch.
Squeeze
Low-volatility compression preceding expansion.
Playbook: Breakout algos primed, directional bet sizing up
Whole market: 23% of the time since 2019, typically lasting ~3 days at a stretch.
What this model would have said, 2019 → now
The live model, run over its full training history — weekly market regime, no hindsight relabeling. Every major crash and bull run is labeled by the exact model serving this page.
COVID crash
2021 bull run
LUNA collapse
FTX collapse
2024 ETF bull
Yen-carry shock
Oct-2025 crash
2020202120222023202420252026
Strong Trend (Bull) · 21% of the timeStrong Trend (Bear) · 13% of the timeRange / Low Volatility · 27% of the timeChoppy High Volatility · 9% of the timeVolatility Spike · 8% of the timeSqueeze · 23% of the time
Per-coin regimes — top Hyperliquid perps by open interest
Each coin gets its own read, conditioned on the whole-market state — SOL can be coiled in a squeeze while the market drifts sideways. Direction numbers are unlocked on the top 3 coins; Pro unlocks all ~178 perps via the API.
The full probability object behind one coin, as readable bars: where price goes, how violent it gets, liquidation pressure, funding, open interest, and which regime comes next.
Direction (next 24h)confidence 6%
Strong fall10%
Mild fall22%
Sideways34%
Mild rise23%
Strong rise11%
Volatility (next 24h)confidence 3%
Low43%
Medium34%
High23%
Liquidation risk (next 24h)confidence 3%
Low43%
Medium34%
High23%
Funding direction (next 24h)confidence 2%
Falls27%
Stable43%
Rises30%
Open interest (next 24h)confidence 0%
Contracting32%
Neutral34%
Expanding34%
Regime transitions (next 24h)confidence 32%
Stays Squeeze51%
→ Range / Low Volatility27%
→ Strong Trend (Bull)13%
→ Strong Trend (Bear)6%
This exact JSON, every 15 minutes, for every coin
Live BTC probability object — including the explain block: feature z-scores, raw state posteriors, the hysteresis rule, raw-vs-calibrated confidence. If you can't audit a probability, you shouldn't trade on it.
We retrospectively scored every hourly regime call this model would have made (56,000+ hours, 2020 → now) against what BTC, 16 major alts and all ~175 Hyperliquid perps actually did next. Here's the honest read — because a probability you can't audit is a probability you shouldn't trade.
It identifies the market state — reliably
The HMM is a nowcast: it tells you which regime the market is in right now, within hours of a state change. During vol_spike, 73–79% of coin-hours across the entire Hyperliquid universe saw elevated volatility over the next 24h. Use it to size positions, widen stops and set liquidation buffers across your whole book.
It routes strategies — measurably
A 24h-momentum strategy that is flat over all hours splits sharply by regime: mean-reversion worked during bear and vol_spike on every dataset we tested (BTC, majors, full HL universe), momentum leaned positive in squeeze. Long-BTC-only-during-bull historically halved max drawdown vs a 200-day trend filter at similar return. Use the regime to pick which strategy runs, not which way to bet.
It does NOT predict direction
P(BTC up next 24h | bull) was 52.8% vs a 52.1% base rate — no edge. And don't short bear: by the time the model flips bearish, ~−2.5% has already happened and the next 7 days averaged positive. The historical timeline above matches price so well because the regime is computed from the move already underway — those bands are recognitions, not calls. No regime model (ours or anyone's) predicts short-horizon direction; vendors who claim otherwise aren't showing you their base rates.
Every number above is reproducible: pull the full point-in-time regime history via GET /api/v1/quant/regimes/history and score it yourself. Calibrated forecast heads (volatility, liquidation-cascade risk, squeeze resolution) with published scorecards are the next release on this engine.
Get it from the API
six regimes with probabilities, per coin and market-widePro
Create a trading strategy using Crypto Market Regimes
Pro
The HMM regime is a nowcast, not a forecast — its measured value is as a strategy SELECTOR: run trend systems in trend regimes, mean-reversion in ranges, and cut size in volatility spikes. That selection is exactly what the 2020-to-now history lets you test.
01 · CONNECTAdd the MCP server to Claude, Cursor or any MCP client — one command, no endpoints to wire up.
02 · PASTEDrop the prompt below into your agent. It already names the live endpoint and the archive to test against.
03 · CHECK ITThe prompt makes the agent report where the edge fails, not just where it works. Read that part first.
PROMPT · paste into your agent/api/v1/quant/market
Build me a regime-switching strategy on the CryptoDataAPI quant regimes.
Read the live market regime from /api/v1/quant/market and per-coin regimes from /api/v1/quant/coins/{symbol}. Assign one sub-strategy per regime — trend-following in the two trend states, mean-reversion in range/low-vol, reduced size or flat in choppy and volatility-spike states — and define what happens to an open position on a regime change.
Then backtest on the point-in-time history at /api/v1/quant/regimes/history (Parquet, 2020 to now, no hindsight relabeling) joined to /api/v1/backtesting/klines.
Compare against running the single best sub-strategy all the time. Report per-regime hit rates. If the switching does not beat the best single strategy after fees, the regimes are not adding selection value — say so.