text-search-davinci-query-001 vs text-embedding-3-small
OpenAI names text-embedding-3-small as the replacement for text-search-davinci-query-001. text-search-davinci-query-001 shut down on Jan 4, 2024. At standard list prices, text-embedding-3-small costs -100% per token (blended 3:1 input:output).
Retired→Active
Per 1M tokenstext-search-davinci-query-001text-embedding-3-small
Input$200$0.02
Output——
Blended change-100%
ProviderOpenAIOpenAI
Statusretiredactive
ShutdownJan 4, 2024—
Context window——
Migrating
- Replace the ID
text-search-davinci-query-001withtext-embedding-3-smalleverywhere it appears, including .env files, config and infrastructure templates. - Run your evaluation set or golden prompts on both before switching: output style, refusals and tool calling can differ between generations.
- Check max output tokens and parameters: newer models sometimes rename or drop sampling options.
- Watch the repo on ModelRot so the next retirement doesn't surprise you. text-embedding-3-small lifecycle.