> For the complete documentation index, see [llms.txt](https://doc.thordata.com/doc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.thordata.com/doc/faq/product-problem/dataset/standard-dataset/fine-tuning-or-rag-which-dataset-should-i-buy.md).

# Fine-tuning or RAG — which dataset should I buy?

It depends on how the knowledge is used and how often it changes. For continuously refreshed facts, use RAG with a [scraping API](https://www.thordata.com/?ls=community\&lk=proxyip) that revisits URLs on a schedule (\~$0.50 per 1,000 results); to change what the model itself knows, buy a one-off structured dataset (JSON/CSV/Parquet) for fine-tuning. Most teams combine both; copyrighted content should not be loaded into training directly. Versus Bright Data's and Oxylabs' enterprise dataset quotes, Thordata lets you trial a small sample first.