TOKENIZER

Overview

Total spend

$2021

6.6%vs prev 30d

Requests

105.3K

8.2%vs prev 30d

Input tokens

274.5M

total

Output tokens

81.8M

total

Cache savings

$334.10

avoided cost

Usage on each agents

Chat Assistant

Real-time conversational responses

Input tokens
Output tokens
Cache write
Cache read

Code Review

Automated code analysis

Input tokens
Output tokens
Cache write
Cache read

Doc Search

Semantic document retrieval

Input tokens
Output tokens
Cache write
Cache read

Tokens & spend

Tokens

COGS

Insights

Spend trend

Spend is up 7% vs the prior 30d period — $2021 this period vs $1897 before.

Cache savings

Prompt caching avoided $334.10 in charges — roughly 14% of what you would have paid without it.

Top cost driver

Chat Assistant drives 57% of total spend — $1143 across 30.1K requests.

Peak traffic

Busiest day was Apr 13 with 10.6K requests. Your p95 daily load is 5.7K requests.

Ask follow-up

Ask anything about your
usage data

Breakdown

Cost by feature

Chat Assistant
30.1K req$1143
Code Review
11.1K req$743.28
Doc Search
64.0K req$134.62

Models used

ModelRequestsInputOutputCost
Claude Sonnet 4.541.3K217.7M61.4M$1887
Claude Haiku 4.564.0K56.8M20.4M$134.62