Llm Model Pricing Context Window Database

Gather large language model (LLM) pricing structures, context window limits, and provider details into a clean, structured dataset. Easily organize models by provider, mode, or input limits, then export your data to JSON, CSV, or Excel formats effortlessly.

What it does

This actor aggregates model specifications into tabular rows that you can filter, schedule, and export. Use it to compare model providers, keep track of context limits, and maintain an organized dataset for cost planning without having to manual-check each model provider.

Modes

• All models: Collects the complete catalog up to your set item limit.
• Filter by provider/mode: Keeps only entries matching specific providers (e.g., OpenAI, Bedrock) or modes like chat or image generation.

Input example

{
  "mode": "filter",
  "providers": ["openai"],
  "modeFilter": "chat",
  "maxItems": 50,
  "requestDelaySecs": 1,
  "userAgent": "ActorResearch/1.0",
  "timeoutSecs": 300,
  "requestTimeoutSecs": 30
}

Output example

{
  "model": "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0",
  "deprecation_date": "2026-09-30",
  "litellm_provider": "bedrock",
  "max_input_tokens": 2600,
  "mode": "image_generation",
  "modelMode": "image_generation",
  "output_cost_per_image": 0.06,
  "scraped_at": "2026-10-26T00:00:00+00:00"
}

The output overview table provides clear details on model name, deprecation status, provider, maximum input tokens, operational mode, image/token cost parameters, and extraction timestamp.

Practical use cases

• Pricing research: Build spreadsheets comparing model costs and context limits to budget software infrastructure.
• Provider comparison: Evaluate offerings from OpenAI, Bedrock, Anthropic, or others side-by-side.
• Product dashboards: Feed structured data into internal tools and software dashboards.
• Cost audits: Save dated snapshots of model metadata for historical tracking and financial reviews.
• Data workflows: Export structured datasets to JSON, CSV, or Excel for analysis.

Frequently asked questions

Who is this tool for?

Developers, researchers, and product teams who want LLM pricing and context window metrics organized in one readable format.

What export formats are supported?

You can export data directly to JSON, CSV, Excel, and other tabular formats supported by Apify datasets.

Can I automate runs?

Yes, you can schedule periodic runs using Apify schedules to keep your dataset updated over time.

Trademark Notice

All product names, logos, brands, and trademarks belong to their respective owners. Their reference here is solely for identification and descriptive purposes, and does not imply endorsement, affiliation, or sponsorship.

Disclaimer

This Actor is an independent collection tool. Users are responsible for ensuring their usage complies with relevant terms, rate limits, and guidelines of target services.

Is web scraping legal?

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

• 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.

This is not legal advice. For the longer explanation, see Apify's article Is web scraping legal?.