LLM Pricing Comparator

What does it do?

LLM Pricing Comparator scrapes LLM API pricing pages from major providers including OpenAI, Anthropic, Google, Mistral, and Cohere. It extracts model names, input and output pricing per million tokens, context windows, and model types so you can compare costs across providers in a single dataset.

The actor runs on the Apify platform and delivers clean, structured data ready for export as JSON, CSV, or Excel. It handles retries, proxy rotation, and varied page formats automatically. Each run stores results in an Apify Dataset that you can download or connect to your workflow via API.

Why use this actor?

• Multi-provider comparison: Compare pricing across OpenAI, Anthropic, Google, Mistral, and Cohere in one run
• Up-to-date pricing: Scrapes live pricing pages for the latest model costs
• Embedding models included: Optionally include embedding model pricing alongside chat models
• Structured output: Clean data with consistent field names for easy analysis and comparison
• Scalable: Run on schedule with Apify Schedules to track pricing changes over time
• Export ready: Download as JSON, CSV, Excel or send to Google Sheets, Slack, webhooks

How to use it

1. Navigate to the LLM Pricing Comparator on Apify Store
2. Select which providers to compare and whether to include embedding models
3. Click Start and wait for results
4. Export the dataset in your preferred format for analysis

You can also run this actor via the Apify API or the Apify JavaScript client.

Input configuration

Field	Type	Description	Default
Providers	array	LLM providers to compare	["openai", "anthropic", "google", "mistral", "cohere"]
Include Embeddings	boolean	Include embedding model pricing	true
Proxy Configuration	object	Proxy settings	Apify Proxy

Output data

Each result contains these fields:

Field	Type	Description
provider	String	Provider name
model	String	Model name
inputPricePerMillion	Number	Input price per million tokens
outputPricePerMillion	Number	Output price per million tokens
contextWindow	String	Maximum context window
type	String	Model type (chat/embedding)
url	String	Source pricing page URL
scrapedAt	String	Timestamp of extraction

Cost of usage

This actor uses pay-per-event pricing. You are charged $0.75 per 1,000 results extracted. Running with default settings typically costs under $0.01. Adjust input parameters to control providers and manage costs.

The actor uses Apify Proxy which is included in your Apify subscription. Memory usage is typically around 256-1024 MB.

Tips and tricks

• Run on a schedule using Apify Schedules to monitor pricing changes over time
• Use Apify integrations to send results to Google Sheets, Slack, Zapier, or your database
• Combine with other actors from the Apify Store for richer data pipelines
• Provider pricing pages change format frequently - the actor includes fallback data for reliability
• Disable embeddings to focus only on chat model pricing comparison

Useful Links

• Apify Platform
• Crawlee Documentation
• Apify SDK
• More actors by consummate_mandala
• GitHub - donnywin85

---

Built with Crawlee and the Apify SDK.