Cloudflare's AI Search starts charging by usage today
The RAG service Cloudflare took generally available on 1 October now bills beyond a free monthly allowance, with separate rates for ingestion, storage and queries.
Cloudflare’s AI Search, its retrieval-augmented-generation service, starts usage-based billing today, a month after reaching general availability on 1 October. Every account still gets a free monthly allowance: 5 million ingestion tokens, 10 GB-month of storage, 1,000 semantic queries and 1,000 full-text queries.
Past that, Cloudflare charges $0.75 per million tokens for ingestion, with image processing adding another $0.50 per million tokens, $2.00 per GB-month for storage, $0.75 per 1,000 semantic or hybrid queries, and $0.10 per 1,000 full-text queries. Workers Paid accounts also get their first 5,000 AI Search instances included, with extra instances costing $0.10 each a month. Workers AI embedding and reranking calls made by AI Search are folded into that pricing too, so they stop appearing on your separate Workers AI bill or in AI Gateway logs.
Why it matters: if you built a RAG pipeline on AI Search during its free preview, your bill changes from today rather than next month, so it’s worth checking your ingestion volume and query counts against the new allowances now.
The caveat: Cloudflare says it emailed a reminder the week before billing started, so check your account email if you missed it.