LLM Prices Tracker

Keep track of current LLM token pricing across various providers in one organized dataset. Filter by specific vendors, limit your run size, and export structured data in JSON, CSV, or Excel formats for quick analysis.

What it does

This actor checks current LLM token rates and structures them into one clear row per model. You get key details like the vendor, model name, and input and output token rates, along with cached input pricing whenever available.

How to run it

Set your preferred options to filter models or limit output, then let the actor collect the data into your workspace.

{
  "vendors": ["openai", "anthropic"],
  "maxItems": 50,
  "requestDelaySecs": 1,
  "userAgent": "ActorResearch/1.0",
  "timeoutSecs": 300,
  "requestTimeoutSecs": 30
}

Sample output

When execution finishes, your dataset will look similar to this structure:

{
  "modelId": "amazon-nova-micro",
  "vendor": "amazon",
  "name": "Amazon Nova Micro",
  "input": 0.035,
  "output": 0.14,
  "inputCached": null,
  "updatedAt": "2026-10-23",
  "scrapedAt": "2026-10-26T00:00:00+00:00"
}

The standard dataset output table presents modelId, vendor, name, input, output, inputCached, and updatedAt for easy reading and export.

Practical applications

• Rate monitoring: Track updates to AI provider pricing on a regular schedule.
• Cost estimation: Import current input and output token rates into spreadsheets to calculate running costs for your prompts.
• Provider comparison: Filter models by provider to compare pricing side by side.
• Reporting dashboards: Export clean datasets straight to CSV or Excel for custom visualization and reporting.

Pricing and usage limits

• Actor compute: Usage is billed based on standard Apify compute unit (CU) consumption while running.
• Custom limits: You can set maxItems to cap the total number of records processed per run, keeping your costs predictable.
• Adjustable delays: Control request timing with requestDelaySecs to stay within rate limits and maintain smooth execution.

FAQ

Who is this actor for?

Developers, data analysts, and product managers who need reliable, updated token pricing without copying figures manually.

What export formats are supported?

You can export results as JSON, CSV, Excel, XML, or HTML directly from your dataset.

Can runs be scheduled automatically?

Yes, you can schedule regular runs to update your rates automatically at chosen time intervals.

How do vendor filters work?

Pass vendor names (like openai or amazon) in your settings. Filtering is flexible and case-insensitive. If left empty, all available models are collected up to your maximum item limit.

Related tools & custom services

If you plan to map or join these rows, a geocoding pass or a quick CSV cleanup are the usual next steps. BigiByte also builds scrapers for other open-data portals when you need them as a separate job. Need another city's open data, a scheduled monitor, or a custom pipeline? BigiByte builds custom scrapers and APIs: https://bigibyte.com

Trademark notice

All product names, logos, and brands mentioned here belong to their respective owners. References in this documentation are used exclusively for identification purposes and do not imply endorsement or official partnership.

Disclaimer

This tool operates independently and is not affiliated with, sponsored by, or endorsed by any vendor listed in the output dataset. Users are expected to follow relevant usage conditions and rate recommendations.

Is web scraping legal?

This actor extracts publicly accessible data without bypassing paywalls, or technical security layers. While collecting public web data is widely permitted, compliance depends on how data is gathered and used:

• Personal data: When collecting identifiers like emails, phone numbers, or social handles, ensure compliance with applicable data protection laws such as GDPR or CCPA.
• Copyrighted content: Public text, images, and visual assets are often protected by intellectual property rights. Avoid directly duplicating or re-distributing full creative works.
• Platform terms & rate limits: Practice responsible data extraction by avoiding aggressive traffic spikes, adhering to rate limits, and respecting published platform policies.
• Disclaimer: This summary serves informational purposes only and does not constitute formal legal counsel. Seek professional legal advice for specific compliance queries.

For a detailed guide, see Apify's legal overview: Is web scraping legal?.