models.dev AI Model Catalog Scraper

Collect a structured catalog of Large Language Models, covering pricing, context windows, capabilities, and modalities across various providers. Choose all providers or narrow your focus to specific ones, set an item limit, and export your data directly into JSON, CSV, or Excel formats.

What it does

This actor flattens model details into ready-to-use dataset rows. Each record organizes core metrics such as pricing structures, token context limits, input/output modalities, and feature flags. so you can easily evaluate and compare models side by side without searching manually.

Modes

• All providers & models: Extract every provider and model into a single dataset.
• Filter provider: Target specific providers (for example, openai or anthropic).

Input example

{
  "mode": "all",
  "maxItems": 50,
  "requestDelaySecs": 1,
  "userAgent": "ActorResearch/1.0",
  "proxyConfiguration": {
    "useApifyProxy": false
  }
}

Filter mode example:

{
  "mode": "provider",
  "providers": ["openai", "anthropic"],
  "maxItems": 100
}

Output example

{
  "provider": "deepinfra",
  "providerName": "Deep Infra",
  "modelId": "tencent/Hy3",
  "name": "Hy3",
  "modelSummary": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
  "family": "Hy",
  "attachment": false,
  "reasoning": true,
  "reasoningOptions": [],
  "toolCall": true,
  "structuredOutput": true,
  "temperature": true,
  "releaseDate": "2026-07-06",
  "lastUpdated": "2026-07-06",
  "modalities": {
    "input": ["text"],
    "output": ["text"]
  },
  "openWeights": true,
  "limit": {
    "context": 262144,
    "input": 192000,
    "output": 128000
  },
  "modelStatus": "deprecated",
  "cost": {
    "input": 0.13,
    "output": 0.53,
    "cache_read": 0.033
  },
  "canonicalModelId": "tencent/hy3",
  "scrapedAt": "2026-10-26T00:00:00+00:00"
}

The dataset view highlights key attributes like provider, providerName, modelId, name, modelSummary, family, and capability flags.

Use cases

• Model comparison: Build clean spreadsheets to compare costs and token limits across different AI providers.
• Capability audits: Quickly filter models by features like reasoning, tool calling, or open weights.
• Product research: Track model releases, updates, and deprecations over time.
• Pipeline feeds: Keep internal dashboards and analytics tools updated with the latest model specs on a set schedule.

FAQ

Who is this for?

Developers, product managers, and data analysts who need structured model metrics for research, benchmarking, or integration.

What formats can I export?

You can download data in JSON, CSV, Excel, and other standard Apify export options.

Can I run it on a schedule?

Yes, you can configure automatic schedules within Apify to refresh your data periodically.

What happens if a request fails?

The actor continues running and records an error entry rather than halting the process.

Trademark Notice

models.dev and related names, logos, and trademarks belong to their respective owners. Their use in this documentation is solely to identify the source of the data and does not imply affiliation, sponsorship, endorsement, or partnership.

Disclaimer

This Actor is an independent tool and is not affiliated with, endorsed by, sponsored by, or otherwise officially associated with models.dev or its owners. All data is collected from publicly available sources. Users are responsible for complying with the source's terms of use and attribution requirements.

Is web scraping legal?

This actor extracts publicly accessible data without bypassing security controls or technical protection 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?