LLMs in the trading research pipeline
Which models Tradewink's pipeline routes calls to, how often, how fast, and at what cost. Models are assigned by subscription tier and task, and the roster changes over time.
Tradewink's public offering is paper trading only, so we don't publish live trading results.
Models are listed by usage, latency, and cost, not by trade outcomes. Any backtest or paper-agent figures below are hypothetical and labeled that way.
Model usage data not yet available
Call volume, latency, and cost appear here once the pipeline has routed calls in the current window.
Methodology
Usage figures aggregate routed-call telemetry over a rolling window: call count, average latency, and average cost per thousand calls. Models are assigned by subscription tier and task, so they do not see the same inputs; the table is an operational report, not a head-to-head test. Tradewink's public offering is paper trading only and does not publish live trading results, so models are not ranked by trade outcomes.
See routed model analysis on your watchlist
Tradewink routes each analysis task to an explicit model for your subscription tier. You can also bring your own model API key.
Important disclosures
Informational purposes only
Tradewink is published by Tradewink LLC, which is not a registered investment adviser, broker-dealer, commodity trading advisor, or financial planner. All data, signals, and analytics on this page are general, impersonal, and for informational purposes only. They do not constitute investment advice, financial advice, or a recommendation to buy or sell any security or other instrument.
Trading risk
Past performance does not guarantee future results. Trading involves substantial risk of loss, including the possibility of losing more than your initial investment. You are solely responsible for your own trading decisions.