Tools and research for putting LLMs into markets.
45 tools that run in your browser and 224 dated articles with the method and every source shown: model costs, market data, backtest validation and agent risk.
Medium (~500 symbols)
| Vendor | Plan | Per year |
|---|---|---|
| Alpaca Markets | Free (IEX feed) | $0 |
| Tiingo | Tiingo Power | $360 |
| Databento | Databento metered (typical retail) | $1,500 |
| Financial Modeling Prep | Ultimate | $1,668 |
| Massive (formerly Polygon.io) | Stocks Advanced | $2,388 |
| Alpha Vantage | No plan fits | — |
What is AI Fin Hub?
A free, independent set of tools and articles for engineers who build with LLMs in trading and finance. The tools work out model and data costs, validate backtests and test agents in a browser tab; the articles carry their formulas and sources, so any number can be checked. It is education, not investment advice, and it has no sponsors or affiliate links.
Start with the decision you need to make
- Plan your agent stack
Estimate first-year cost for an LLM agent — token budget, vendor selection, MCP servers.
- Validate your strategy
Pressure-test a quant or LLM-augmented strategy before paper-trading or production.
- Audit your pipeline
Catch hallucinations, prompt injections, and regression drift before they ship.
- Size your bets
Compute Kelly fraction, drawdown bounds, and correlated exposure across a book.
- Explore market structure
Inspect order books, options payoffs, and cross-venue arb in a sandbox before going live.
Contents
All 45 tools on one pageCalculators 16
Inputs to numbers you can act on
- Agent Cost Envelope Calculator Model an LLM research loop end-to-end — steps, tool calls, convergence checks, markets per day — and see per-loop, daily, and monthly cost with cost-cap.
- Backtest Overfitting Score Upload a backtest trade log and compute Probability of Backtest Overfitting (PBO), Deflated Sharpe Ratio, and the odds your edge survives live trading.
- Batch vs Real-Time Cost Calculator Jobs per day, tokens per job, model, deadline — get real-time vs batch cost side-by-side with savings estimate and batch-eligibility flag. Based.
- Deflated Sharpe Ratio Calculator Bailey & López de Prado deflated Sharpe — corrects observed Sharpe for selection bias across K trials. Reports deflated Sharpe, PSR (probability of skill).
- Drawdown-Recovery Markov Simulator Time to recover from an N% drawdown given monthly Sharpe + skew + kurtosis. Cornish-Fisher Monte Carlo, percentile distribution of recovery months.
- Earnings-Call Summarization Cost Calculator LLM cost per stock per quarter to summarize earnings transcripts across Sonnet, Opus, GPT-5.5, Gemini 2.5 Pro/Flash. Cache-hit-rate aware. Snapshot pricing.
- Efficient Frontier Calculator Paste a multi-asset returns CSV. See the Markowitz mean-variance frontier, the minimum-variance portfolio, the max-Sharpe (tangency) portfolio.
- Financial Document Token Estimator Paste a 10-K, 10-Q, 8-K or earnings transcript and see token count + one-pass extraction cost across ten frontier LLMs, with cache-hit toggle.
- Kelly Criterion Calculator Size positions with full, half, quarter, or eighth Kelly and stress-test the choice with a drawdown Monte Carlo simulator.
- Portfolio Correlation Matrix Paste a multi-asset returns CSV. See the Pearson correlation heatmap, condition number, average absolute correlation, and eigenvalue concentration.
- Position Sizing under Edge Variance Bayesian-Kelly bet sizing when your edge is itself uncertain. Compare deterministic Kelly, Bayesian-adjusted, and conservative lower-bound versions.
- Returns Distribution Analyzer Paste a returns CSV. Histogram, normal QQ plot, skewness, excess kurtosis, Jarque-Bera test, tail-weight index. See why Sharpe alone misleads.
- Risk-Adjusted Returns Calculator Paste a returns CSV. Sharpe, Sortino, Calmar, Omega, alpha, beta, tracking error, information ratio, max drawdown, and tail moments — plus.
- Sharpe Ratio Calculator Paste daily returns; get Sharpe, Sortino, Calmar, and Omega side-by-side with a recommendation on which ratio fits your distribution.
- Statistical Arbitrage Capacity Calculator Maximum strategy AUM from alpha, slippage, fees, daily volume and volatility, and signal half-life. Square-root impact closed-form.
- Token-Cost Optimizer Compute the dollar cost of a trading research loop across Claude, GPT, and Gemini. Prompt length × model × retry × call volume → cost per idea and per.
Comparators 5
Vendors and models side by side
- Broker API Comparator Alpaca vs IBKR vs Tradier vs Schwab vs Robinhood — compare auth, rate limits, order types, market data, MCP, and fees before wiring a line of code.
- FTC vs FCA vs MiCA+DORA Regulatory Cost Compare US (FTC), UK (FCA), and EU (MiCA + DORA) compliance cost for an AI-finance product. Snapshot data with as-of date — not legal advice.
- Kalshi vs Polymarket Arb Scanner Daily-refreshed scan of arbitrage candidates across Kalshi and Polymarket. Paired contract matching, tax + resolution-risk overlay, no signup. Edge data.
- Market Data API Cost Calculator Compute annual cost of market data across Databento, Polygon, Alpaca, Tiingo, FMP, and Alpha Vantage for your exact universe, bar resolution, and real-time needs.
- Model Selector for Finance Input task, latency budget, cost budget, context size, and quality sensitivity; get ranked model recommendations with rationale — grounded in published.
Playgrounds 19
Test agents, prompts and models
- Agent Skill Tester for Markets Paste a SKILL.md definition + sample input + your Anthropic API key. See structured extraction, token cost, and latency — all in your browser.
- Calibration Dojo Train your probabilistic intuition. Answer binary forecasting questions at any confidence level; track Brier score and reliability curve over time. All.
- Cointegration Half-Life Solver Engle-Granger residual ADF + Ornstein-Uhlenbeck half-life from any two price/return series. Hedge ratio, p-value, spread chart.
- Execution Simulator Estimate execution cost in closed form — square-root permanent impact, linear temporary impact, half-spread, and a latency-drift band. See the slippage a naive backtest hides.
- Fallback Chain Simulator Define a provider fallback chain, simulate rate-limit and latency failures, and see p50/p95/p99 latency, success rate, total cost, and the degradation-event distribution.
- Forecast Scoring Sandbox Paste a forecast stream (probability + outcome) and see Brier score with full decomposition, log loss, reliability diagram, and bootstrap confidence.
- Hallucination Detector Paste a source document + an LLM's extraction. Every numeric claim in the output is checked against the source. Client-side. Catches silent fabrication.
- LLM Finance Error Taxonomy 12 documented LLM-on-finance failure modes (hallucinated ticker, stale price, units, currency, off-by-100, fictional source, more). Paste output, see flags.
- Options Greeks Calculator Black-Scholes pricer + live Greeks visualizer. Drag spot, strike, vol, DTE, rate, dividend yield — see delta, gamma, theta, vega, rho update.
- Options Payoff Calculator Build 1–4 leg option strategies. Pick call/put, long/short, strike, and contracts. See the at-expiry payoff diagram, break-even points, maximum profit.
- Order Book Replay Visualizer Drop a Level-2 snapshot CSV and replay the book snapshot by snapshot. Animated depth bars, best bid/ask, spread and imbalance. Understand microstructure before.
- Pair Trading Cointegration Tester Paste two price series. Engle-Granger cointegration test: OLS hedge ratio, Augmented Dickey-Fuller on residuals, Ornstein-Uhlenbeck half-life, z-score.
- Price-Blind Research Auditor Paste a research prompt or agent context bundle. The auditor flags price numbers, directional words, and outcome-leaking phrases that cause LLMs.
- Prompt Injection Tester Red-team a finance agent against 23 documented prompt-injection attacks — direct override, role confusion, indirect injection via retrieved content.
- Prompt Regression Tester Run the same prompt against multiple models (Claude 4.5/4.6/4.7, GPT-5, Gemini 2.5) with your own keys. Diff outputs, score drift, catch regressions.
- Structured Schema Validator for Finance Paste LLM JSON output and validate against four pre-built finance schemas — research output, trade decision, risk snapshot, peer comparison — with sanity.
- VaR Backtest — Kupiec & Christoffersen Paste P&L + VaR series and run Kupiec POF, Christoffersen independence, and joint conditional-coverage tests. Likelihood-ratio χ² p-values.
- Walk-Forward Validation Visualizer Paste a strategy returns CSV, get per-window in-sample vs out-of-sample Sharpe and the IS→OOS drop. Rolling and anchored window modes.
- Walk-Forward Validator Upload a returns CSV. Rolling or expanding IS/OOS windows, per-window Sharpe, walk-forward efficiency, and a concatenated OOS equity curve. Catches regime.
Generators and catalogs 5
Blueprints, configurations and directories
- Finance MCP Directory Security-graded catalog of finance MCP servers — Alpaca, Polygon, Databento, IBKR, Tradier, Tiingo, NautilusTrader. Scope, auth, idempotency, transport.
- Quant Interview Question Generator Curated bank of probability, stats, derivatives, microstructure, and regression questions across easy/medium/hard difficulty. Reproducible by seed. Nothing generated live.
- SEC Filing Chunk Optimizer Pick a filing archetype, tune chunk size and overlap, and see chunk count, embedding cost, and structural-boundary warnings across three chunking strategies.
- Synthetic Market Data Generator Generate synthetic price series — geometric Brownian motion, GARCH(1,1) with volatility clustering, regime-switching bull/bear, or copula-linked.
- Trading System Blueprinter Pick your data source, LLM, broker, storage, risk engine, and logger. Get a Mermaid architecture diagram and a copyable starter file tree — the full stack before you write code.
Research
All 224 articles- Reading Financial Filings With LLMs: 2026 Playbook
A map of eight filing tasks — extraction, summarization, peer comparison, Q&A, classification, sentiment, forecasting input, compliance — with model.
14-minute read, April 23, 2026
- Model Selection Framework for Finance Tasks
A task × latency × cost × context decision tree for finance LLM workloads. Ten concrete scenarios mapped to tier bands. Grounded in published pricing, not.
12-minute read, April 23, 2026
- State of LLM Pricing for Finance Q3 2026
Vendor pricing for 21 LLM tiers across six providers — Anthropic Opus 4.8 + Fable 5, OpenAI GPT-5.5, Google Gemini 3.5 Flash, xAI Grok 4.3, DeepSeek V4, Mistral.
18-minute read, June 21, 2026
Pricing benchmarks are dated and re-checked against vendor pages: all benchmarks.
Vendor and API pricing
- Broker API rate limits 2026
Request caps, order types and option-chain polling at Interactive Brokers, Alpaca, Tradier and Schwab.
- Polygon.io (Massive) pricing 2026, plan by plan
Every Stocks tier from free Basic to $199 Advanced, with annual prices and the other asset-class ladders.
- Market data API pricing 2026
Massive, Databento, Alpaca, Tiingo, FMP and Alpha Vantage, matched to the workload.
- Polygon.io to Massive migration
What changed for engineers: API hosts, SDK packages, WebSocket and flat-file endpoints.
- Polygon.io futures, forex and options
What Massive covers beyond stocks, and what each real-time plan costs.
- Finnhub free tier and pricing 2026
The 60-calls-per-minute free tier, the paid ladder and the commercial-use catch.
- FMP API pricing 2026
Free Basic at 250 calls a day, then $29, $69 and $139 a month, and the display licence.
Reference
- Glossary
Risk, backtesting and market-structure terms, defined with an example each
- Formulas
The equations the tools run, with worked examples
- Worked examples
Real inputs through the calculators, reproducible
- Guides
Task-first how-tos for AI in markets
- Checklists
Pre-flight sign-off lists
- Comparisons
Side-by-side decision tables
- Statistics
Sourced AI-in-finance figures
- Reference grids
Lookup tables computed by the tools
- Alternatives
Switching options for each data and broker vendor