Cut your token costs by 40-70%
Actor output is full of low-value data that wastes LLM tokens: raw HTML, internal IDs, timestamps, debug fields. LLM Output Optimizer scores every field by information density, recommends what to drop, and shows exactly how many tokens you'll save.
Calculates token cost for every field across your sample output using character-based approximation (~4 chars/token).
Scores each field as high-value (name, url, email), medium-value (generic), or low-value (IDs, timestamps, raw HTML).
Fields with >80% null values are flagged for removal — they waste tokens on empty data.
Fields averaging >500 characters (raw HTML, page content) are flagged for truncation or removal.
Generates a recommended field list that keeps high-value data and drops the rest.
Original vs optimized token count with percentage — see the exact impact before making changes.
{
"actorName": "ryanclinton/website-contact-scraper",
"originalTokens": 4200,
"optimizedTokens": 1680,
"savingsPercent": 60,
"fieldAnalysis": [
{ "field": "rawHtml", "tokens": 2800, "value": "low", "action": "drop" },
{ "field": "url", "tokens": 45, "value": "high", "action": "keep" },
{ "field": "emails", "tokens": 120, "value": "high", "action": "keep" }
],
"optimizedSchema": ["url", "domain", "emails", "phones"],
"recommendations": ["Drop 3 low-value fields — saves 60%"]
}Connect your Apify token and enter the actor ID
The tool runs the actor on your account and analyzes the output
Get a detailed report with actionable fixes — results cached for free