by OpenAI·Released 12 March 2025
GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.
Reads about 120 pages · writes up to 16 pages
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokensStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsOther
Also accepted by this model.
web_search_optionsNo. OpenAI has retired it. Other OpenAI models are on sale.
The lab has not said.
OpenAI names no languages for GPT-4o-mini Search Preview. Arabic, French and Darja: not stated.
It reads text. Up to 128K tokens in one request, about 120 pages. It writes up to 12 000 words at once.
No. OpenAI has not published its weights.
OpenAI. Released 12 March 2025. It knows the world up to 31 October 2023.
Text Embedding 3 Small turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It replaces the older ada-002 and is the sensible default for search over your documents, grouping similar messages or labelling them.
GPT Image 2.5 Sunburst takes a written description, with optional reference pictures, and gives back an image, new or edited, as PNG, JPEG or WebP, with transparent backgrounds on PNG and WebP. It is the precision tier of the 2.5 series, for detailed creative work where an edit has to land exactly as asked, and it adds top quality settings named xhigh and max.
GPT-6 Luna Decisions does not write text. You send content as text, a table of data or a picture, plus up to 200 named questions of three kinds: yes or no, pick among options, or grade against an ordered scale. It returns a probability for every answer, with the likeliest option or expected score, so your own system can set its thresholds for routing, moderation or marking.
Text Embedding 3 Large turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It is the most accurate of OpenAI's models of this kind, in English and other languages. Choose it when the quality of matches matters most, for search, grouping or labelling documents.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first No.
Works through the problem before it answers.
Uses your tools No.
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web
Can look things up online while it answers.
Cheaper on repeats No.
A prompt it saw a moment ago costs less the second time.
Knows events up to 31 Oct 2023
What it learned stops at this date.