For teams building retrieval augmented generation or semantic search who need to budget the indexing step. You get total tokens, the one-time embedding cost and the cost per 1,000 documents.
Build industry projects on ByteLabs and add verified proof of your skills to your public profile.
You enter
10,000 chunks of 512 tokens, text-embedding-3-small at $0.02 per 1M
The tool shows
Total tokens 5,120,000; one-time embed cost $0.1024; per 1k docs about $0.0102 (estimate rate)
At an estimate rate of $0.02 per 1M tokens it is two cents, and at $0.13 per 1M it is 13 cents. The rates in the tool are editable estimates, not live quotes.
Indexing a corpus is mostly one-time, but you pay again to re-embed changed documents, when you switch embedding models, and for every user query you embed at search time.
The total tokens embedded is roughly the corpus size, so chunk size matters little, but overlap adds tokens. Use the RAG Chunk Calculator to include overlap.
Yes. It is free, needs no sign-up and runs entirely in your browser, so what you type is not uploaded. You only sign in if you want to email a result to yourself or save it to your CareerByteCode profile.
