Token Usage Analytics: Track & Optimize Your AI Spending

Where Are Your Credits Going?

Most teams have no idea which prompts, users, or projects consume the most AI credits. Token analytics gives you full visibility with breakdowns by model, endpoint, user, and time period.

The Analytics Dashboard

Real-time charts show token consumption, cost trends, and efficiency metrics. Drill down into individual requests or zoom out to monthly summaries.

import Vincony from "vincony";

const client = new Vincony({ apiKey: "YOUR_API_KEY" });

// Get usage analytics
const analytics = await client.analytics.usage({
  period: "last_30_days",
  group_by: ["model", "endpoint"],
  metrics: ["tokens", "cost", "requests", "avg_latency"]
});

analytics.breakdown.forEach(item => {
  console.log(`${item.model}: ${item.tokens.toLocaleString()} tokens, ${item.cost.toFixed(2)}`);
});

// Set budget alerts
await client.analytics.alerts.create({
  type: "daily_spend",
  threshold: 50.00,
  notify: ["email", "slack"]
});

Cost Optimization Recommendations

The analytics engine automatically identifies optimization opportunities: prompts that could use cheaper models, redundant requests, and caching opportunities that could save 20-40% on token spend.

// Get optimization suggestions
const suggestions = await client.analytics.optimize();

suggestions.forEach(s => {
  console.log(`${s.recommendation}: Save ~${s.estimated_savings}/month`);
});
// "Switch summarization tasks to gemini-2-flash: Save ~$45/month"
// "Enable response caching for repeated queries: Save ~$32/month"

Team & Project Budgets

Set per-team and per-project budgets with automatic throttling when limits approach. No more surprise bills at the end of the month.

Pricing

Basic analytics are included on all plans. Advanced breakdowns, optimization recommendations, and budget controls are available on Pro and Enterprise.