Vercel Ai Gateway Models Scraper

BigiByte brings you the Vercel AI Gateway Models Scraper. a specialized extraction utility designed to effortlessly collect comprehensive language model inventories, capabilities, and detailed pricing structures. Whether you are conducting competitive research, tracking context windows, or building pricing comparison tables, this tool retrieves clean, structured datasets in JSON, CSV, or Excel formats with minimal friction.

What it does

This actor reads the available model records from the gateway catalog, allowing developers, product managers, and AI researchers to inspect provider offerings, context limits, tags, and pricing parameters within a single unified dataset. The crawler fetches structured model catalogs and caps the output cleanly based on your custom item limit.

Modes

• All models: Fetches every available model from the complete catalog, with optional provider filtering.

Input example

{
  "mode": "models",
  "ownedBy": ["openai", "anthropic"],
  "maxItems": 50,
  "requestDelaySecs": 1,
  "userAgent": "ActorResearch/1.0",
  "requestTimeoutSecs": 30
}

Output example

{
  "modelId": "alibaba/qwen-3-14b",
  "modelObject": "model",
  "created": 1755815280,
  "released": 1745798400,
  "ownedBy": "alibaba",
  "modelName": "Qwen3-14B",
  "modelSummary": "Qwen3 is the latest generation of large language models in Qwen series.",
  "contextWindow": 40960,
  "maxTokens": 16384,
  "modelKind": "language",
  "zdr": "all",
  "noTraining": "all",
  "tags": ["reasoning", "tool-use", "structured-output", "open-weights"],
  "supportedSpecifications": ["v2", "v3", "v4"],
  "modalities": {"input": ["text"], "output": ["text"]},
  "supportedParameters": ["max_tokens", "temperature", "stop"],
  "temperature": true,
  "reasoningOptions": [{"type": "toggle"}],
  "knowledge": "2025-04",
  "pricing": {"input": "0.00000012", "output": "0.00000024"},
  "scrapedAt": "2026-10-26T00:00:00+00:00"
}

The overview table presents key attributes including modelId, modelObject, created, released, ownedBy, modelName, and modelSummary.

Use cases

• Model discovery: Explore providers, architectures, and model variants available across the ecosystem
• Pricing comparison: Extract granular input and output pricing fields for cost modeling and spreadsheet analysis
• Capability filtering: Filter and organize tags such as reasoning or tool-use for tailored shortlists
• Context planning: Verify contextWindow and maxTokens specifications before building integrations
• Catalog monitoring: Set up regular collection runs to track newly released models or deprecations over time

Pricing and Usage Limits

• Cost-effective extraction: Runs efficiently with adjustable request delays and timeout settings to match your throughput requirements.
• Adjustable batching: Control the maximum item count per run to fit within your resource budget.

FAQ

Who is this for?

Engineers, data analysts, and AI researchers who need structured model catalogs in spreadsheets or automated pipelines.

What formats can I export?

JSON, CSV, Excel, and all standard dataset export options supported by the platform.

Can I run this on a schedule?

Yes, you can configure recurring runs to automatically refresh your model datasets.

How do I filter by specific providers?

Simply specify one or more provider slugs (such as openai or anthropic) in the filter settings.

Related tools

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 open dataset, 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 are property of their respective owners. Their use is strictly for identification purposes and does not imply official endorsement, sponsorship, or partnership with BigiByte.

Disclaimer

This Actor is an independent utility developed by BigiByte and is not officially associated with or endorsed by Vercel. Users are solely responsible for ensuring compliance with applicable platform terms, policies, and rate limits.

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?