AI Usage Chart

Token consumption, model costs, request throughput, and latency — with SVG charts, metric cards, and model breakdown.

AI Usage & API Token Analytics

Live API

Monitor token consumption, model costs, request throughput, and latency.

Monthly budget: $37.20 of $100.00 (37% consumed)

Normal

tokens trend (7d)Peak: 495,000

MonTueWedThuFriSatSun

LLM model consumption

4 active models

GPT-4o

1.1M tokens$17.8048%

Claude 3.5 Sonnet

740K tokens$12.4032%

Gemini 1.5 Pro

320K tokens$4.9014%

DeepSeek V3

140K tokens$2.106%

API Cost Overview

Billing

Monitor token consumption, model costs, request throughput, and latency.

Monthly budget: $112.40 of $150.00 (75% consumed)

Normal

cost trend (30d)Peak: 41.2 $

Week 1Week 2Week 3Week 4

LLM model consumption

4 active models

GPT-4o

1.1M tokens$17.8048%

Claude 3.5 Sonnet

740K tokens$12.4032%

Gemini 1.5 Pro

320K tokens$4.9014%

DeepSeek V3

140K tokens$2.106%

AI Usage & API Token Analytics

Live API

Monitor token consumption, model costs, request throughput, and latency.

latency trend (24h)Peak: 240

00:0004:0008:0012:0016:0020:0023:59