Pricing

from $50.00 / 1,000 audit — up to 100k tokens

Try for free

Go to Apify Store

AI Agent Cost & Token Savings Auditor

Try for free

Find wasted tokens, cache misses and unnecessary agent cost — without sending prompts or content. Free estimate first; the full audit is charged by trace size.

Pricing

from $50.00 / 1,000 audit — up to 100k tokens

Rating

0.0

(0)

Developer

Marko Ciric

Actor stats

Bookmarked

Total users

Monthly active users

a month ago

Last modified

Categories

Developer tools

You can access the AI Agent Cost & Token Savings Auditor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4# Replace '<YOUR_API_TOKEN>' with your token.
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7# Prepare the Actor input
8run_input = { "auditCapsule": {
9        "schema": "audit-capsule/1.0",
10        "runId": "run_demo_001",
11        "durationMs": 18260,
12        "events": [
13            {
14                "schema": "runtime-event/1.0",
15                "eventId": "evt_1",
16                "runId": "run_demo_001",
17                "timestampMs": 1757000000000,
18                "type": "MODEL_CALL",
19                "nodeId": "planner",
20                "nodeType": "AGENT",
21                "provider": "anthropic",
22                "model": "claude-sonnet-5",
23                "inputTokens": 2100,
24                "cachedInputTokens": 0,
25                "cacheWriteTokens": 46000,
26                "outputTokens": 520,
27                "latencyMs": 2140,
28                "status": "SUCCESS",
29            },
30            {
31                "schema": "runtime-event/1.0",
32                "eventId": "evt_2",
33                "runId": "run_demo_001",
34                "timestampMs": 1757000004200,
35                "type": "MODEL_CALL",
36                "nodeId": "researcher",
37                "nodeType": "AGENT",
38                "provider": "anthropic",
39                "model": "claude-sonnet-5",
40                "inputTokens": 1400,
41                "cachedInputTokens": 46000,
42                "cacheWriteTokens": 0,
43                "outputTokens": 880,
44                "latencyMs": 1310,
45                "status": "SUCCESS",
46            },
47            {
48                "schema": "runtime-event/1.0",
49                "eventId": "evt_3",
50                "runId": "run_demo_001",
51                "timestampMs": 1757000009600,
52                "type": "MODEL_CALL",
53                "nodeId": "researcher",
54                "nodeType": "AGENT",
55                "provider": "anthropic",
56                "model": "claude-sonnet-5",
57                "inputTokens": 1900,
58                "cachedInputTokens": 46800,
59                "cacheWriteTokens": 0,
60                "outputTokens": 640,
61                "latencyMs": 1180,
62                "status": "SUCCESS",
63            },
64            {
65                "schema": "runtime-event/1.0",
66                "eventId": "evt_4",
67                "runId": "run_demo_001",
68                "timestampMs": 1757000014800,
69                "type": "MODEL_CALL",
70                "nodeId": "writer",
71                "nodeType": "AGENT",
72                "provider": "anthropic",
73                "model": "claude-sonnet-5",
74                "inputTokens": 49300,
75                "cachedInputTokens": 0,
76                "cacheWriteTokens": 0,
77                "outputTokens": 1240,
78                "latencyMs": 3460,
79                "status": "SUCCESS",
80            },
81        ],
82    } }
83
84# Run the Actor and wait for it to finish
85run = client.actor("truesoft/ai-agent-cost-token-savings-auditor").call(run_input=run_input)
86
87# Fetch and print Actor results from the run's dataset (if there are any)
88print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
89for item in client.dataset(run.default_dataset_id).iterate_items():
90    print(item)
91
92# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

AI Agent Cost & Token Savings Auditor API in Python

The Apify API client for Python is the official library that allows you to use AI Agent Cost & Token Savings Auditor API in Python, providing convenience functions and automatic retries on errors.

Install the apify-client

$pip install apify-client

Other API clients include:

AI Agent Cost & Token Savings Auditor API in JavaScript

AI Agent Cost & Token Savings Auditor API through CLI

AI Agent Cost & Token Savings Auditor OpenAPI definition

AI Agent Cost & Token Savings Auditor API

AI Web Scraper

apify/ai-web-scraper

AI-first web scraper that extracts structured data from any website using natural-language prompts. No programming knowledge required. No hard-coded logic that breaks when a website changes.

Apify

10K

4.9

(15)

AI Image Generator & Editor: Nano Banana, Flux, Logo & Upscale

pnda/ai-image-generator

Bulk AI image generator and editor (up to 100 prompts per run): Flux, GPT Image 2, Seedream, Imagen 4, Ideogram, Nano Banana editing, SVG logos and upscaling, no API key. From $0.02 per image. Works with a free Apify account too (1 image/month, FLUX Schnell). For videos, use pnda/ai-video-generator.

PNDA

5.0

(3)

AI Product Recommendation Agent

matymar/ai-product-recommendation-agent

The AI Product Recommendation Agent helps users find the best products based on their needs using a simple query. It analyzes product listings, reviews, and ratings to provide well-informed recommendations.

Matouš Mařík

105

1.7

(3)

Job Search Assistant AI Agent

harvestlabs/job-search-assistant-ai-agent

Automates the process of finding job listings based on user-defined preferences. Analyzes job postings, scores them based on relevance, and even generates tailored cover letters for each opportunity.

harvest-org

104

4.6

(2)

AI Extraction Agent - Smart Scraper

alizarin_refrigerator-owner/ai-extraction-agent

AI-powered data extraction using natural language prompts. Describe what you need & let AI extract structured data from any webpage automatically.

The Howlers

AI Real Estate Agent

harvestlabs/ai-real-estate-agent

Given a user's input the agent extracts key criteria, searches relevant real estate listings, and outputs a multi-format report.

harvest-org

233

AI Search Visibility Audit

responsible_bookmark/ai-search-visibility-audit

Audits websites for AI search readiness — scores how likely pages are to be cited by ChatGPT, Perplexity, Gemini, Claude, Copilot, Grok, and Google AI Overviews / AI Mode across 6 categories: crawlability, entity clarity, content structure, schema markup, authority signals, AI-specific optimisation.