Skip to main content 首页 创作者 comeonoliver skillshub clay-cost-tuning
clay-cost-tuning Optimize Clay credit spending with provider key management, waterfall tuning, and budget controls.
Use when analyzing Clay costs, reducing credit consumption,
or implementing spending alerts and caps.
Trigger with phrases like "clay cost", "clay billing", "reduce clay costs",
"clay pricing", "clay expensive", "clay budget", "clay credits".
跳到安装 Skills Marketplace 发现并探索由社区构建的 Agent Skills
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ComeOnOliver/skillshub --skill clay-cost-tuning命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
下载 Zip 下载中... name clay-cost-tuning description Optimize Clay credit spending with provider key management, waterfall tuning, and budget controls.
Use when analyzing Clay costs, reducing credit consumption,
or implementing spending alerts and caps.
Trigger with phrases like "clay cost", "clay billing", "reduce clay costs",
"clay pricing", "clay expensive", "clay budget", "clay credits".
allowed-tools Read, Write, Edit, Grep version 1.0.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> compatible-with claude-code, codex, openclaw tags ["saas","clay","api","monitoring","cost-optimization"]
Clay Cost Tuning
Overview
Reduce Clay data enrichment spending by connecting your own API keys (70-80% savings), optimizing waterfall depth, improving input data quality, and implementing budget controls. Clay's March 2026 pricing split credits into Data Credits and Actions, changing the optimization calculus.
Prerequisites
Clay account with visibility into credit consumption
Understanding of which enrichment columns are in your tables
Access to Clay Settings > Plans & Billing
Instructions
Step 1: Connect Your Own Provider API Keys (Biggest Savings)
This is the single most impactful cost reduction. Clay charges 0 Data Credits when you use your own API keys:
Provider Clay-Managed Cost Own Key Cost Annual Savings (10K rows/mo) Apollo 2 credits/lookup 0 credits ~240K credits/year Clearbit 2-5 credits 0 credits ~360K credits/year Hunter.io 2 credits 0 credits ~240K credits/year Prospeo 2 credits 0 credits ~240K credits/year People Data Labs 3 credits 0 credits ~360K credits/year ZoomInfo 5-13 credits 0 credits ~1M+ credits/year
Setup: Go to Settings > Connections in Clay, click Add Connection , and paste your provider API key. All enrichments using that provider will consume 0 Clay credits (1 Action is still consumed per enrichment).
Step 2: Optimize Waterfall Enrichment Depth
Each waterfall step costs credits (if using Clay-managed keys) and time:
expensive:
- apollo: 2 credits
- hunter: 2 credits
- prospeo: 2
credits
-
dropcontact:
3
credits
-
findymail:
3
credits
total_max:
12
credits/row
coverage:
~92%
optimized:
-
apollo:
2
credits
-
hunter:
2
credits
total_max:
4
credits/row
coverage:
~83%
savings:
"67% credit reduction, ~9% coverage loss"
March 2026 change: Failed lookups no longer cost Data Credits. This makes wider waterfalls less expensive than before, since you only pay when data is actually found.
Step 3: Pre-Filter Input Data Credits wasted on unenrichable rows are the most common cost leak:
function estimateCreditCost (rows : any [], creditsPerRow : number filteredRows : any [];
estimatedCredits : number ;
savings : number ;
} {
const personalDomains = new Set ([
'gmail.com' , 'yahoo.com' , 'hotmail.com' , 'outlook.com' , 'icloud.com' ,
]);
const filtered = rows.filter (row =>if (!row.domain ?.includes ('.' )) return false ;
if (personalDomains.has (row.domain )) return false ;
if (!row.first_name || !row.last_name ) return false ;
return true ;
});
const seen = new Set <string >();
const deduped = filtered.filter (row =>const key = `${row.domain} :${row.first_name} :${row.last_name} ` .toLowerCase ();
if (seen.has (key)) return false ;
seen.add (key);
return true ;
});
return {
filteredRows : deduped,
estimatedCredits : deduped.length * creditsPerRow,
savings : (rows.length - deduped.length ) * creditsPerRow,
};
}
const { filteredRows, estimatedCredits, savings } = estimateCreditCost (rawLeads, 6 );
console .log (`Will process ${filteredRows.length} rows (${estimatedCredits} credits)` );
console .log (`Saved ${savings} credits by pre-filtering` );
Step 4: Use Sampling Before Full Runs Test enrichment quality on a small sample before committing credits to the full list:
function sampleForTest (rows : any [], sampleSize = 100 sample : any [];
remaining : any [];
estimatedTotalCredits : number ;
} {
const shuffled = [...rows].sort (() => Math .random () - 0.5 );
const sample = shuffled.slice (0 , sampleSize);
const remaining = shuffled.slice (sampleSize);
return {
sample,
remaining,
estimatedTotalCredits : rows.length * 6 ,
};
}
Step 5: Implement Credit Budget Alerts
interface CreditBudget {
monthlyLimit : number ;
dailyThreshold : number ;
perTableMax : number ;
}
const PLAN_BUDGETS : Record <string , CreditBudget > = {
launch : { monthlyLimit : 2_500 , dailyThreshold : 125 , perTableMax : 500 },
growth : { monthlyLimit : 6_000 , dailyThreshold : 300 , perTableMax : 1_500 },
enterprise : { monthlyLimit : 50_000 , dailyThreshold : 2_500 , perTableMax : 10_000 },
};
class BudgetMonitor {
private dailyUsage = 0 ;
private monthlyUsage = 0 ;
private tableUsage = new Map <string , number >();
constructor (private budget : CreditBudget recordUsage (tableId : string , credits : number this .dailyUsage += credits;
this .monthlyUsage += credits;
this .tableUsage .set (tableId, (this .tableUsage .get (tableId) || 0 ) + credits);
if (this .dailyUsage > this .budget .dailyThreshold ) {
console .warn (`ALERT: Daily credit usage (${this .dailyUsage} ) exceeds threshold (${this .budget.dailyThreshold} )` );
}
if (this .monthlyUsage > this .budget .monthlyLimit * 0.8 ) {
console .warn (`ALERT: Monthly credits at ${((this .monthlyUsage / this .budget.monthlyLimit) * 100 ).toFixed(0 )} %` );
}
if ((this .tableUsage .get (tableId) || 0 ) > this .budget .perTableMax ) {
console .error (`STOP: Table ${tableId} exceeded per-table cap (${this .budget.perTableMax} credits)` );
}
}
}
Step 6: Credit-Per-Lead Cost Calculator function calculateCostPerLead (
totalCredits : number ,
totalRows : number ,
rowsWithEmail : number ,
rowsPushedToCRM : number ,
): void {
console .log ('=== Clay Cost Analysis ===' );
console .log (`Credits used: ${totalCredits} ` );
console .log (`Cost per row processed: ${(totalCredits / totalRows).toFixed(1 )} credits` );
console .log (`Cost per email found: ${(totalCredits / Math .max(rowsWithEmail, 1 )).toFixed(1 )} credits` );
console .log (`Cost per CRM lead: ${(totalCredits / Math .max(rowsPushedToCRM, 1 )).toFixed(1 )} credits` );
console .log (`Email find rate: ${((rowsWithEmail / totalRows) * 100 ).toFixed(1 )} %` );
console .log (`Qualification rate: ${((rowsPushedToCRM / totalRows) * 100 ).toFixed(1 )} %` );
}
Error Handling Issue Cause Solution Credits burning fast Waterfall enriching all providers Enable "stop on first result", reduce depth Low hit rate (<30%) Bad input data Filter personal domains, validate before import Unexpected charges New column added with auto-run Review all auto-run columns monthly Credit rollover capped Balance exceeds 2x monthly Use credits before they cap out
Resources
Next Steps For reference architecture patterns, see clay-reference-architecture.
