GPT-4o MINI - 1st Comparison & Test

New GPT-4o mini in a first performance test for its VLM functionalities - its VISION AI .
GPT-4omni mini has a context window of 128K tokens, supports up to 16K output tokens per request, and has knowledge up to October 2023.
Developers pay 15 cents per 1M input tokens and 60 cents per 1M output tokens (roughly the equivalent of 2500 pages in a standard book).
all rights w/ OpenAI:
openai.com/ind...
#airesearch #ai #science

[@marcfruchtman9473]

Great stuff. Thanks for the video. I am impressed with mini, especially the level of organized output.

[@andydataguy]

You mentioned a video about AtomAgent but i dont see it on your channel

[@propeacemindfortress]

cool

[@tomw4688]

at the last comparison you were comparing claude 3.5 sonnet with GPT-4o instead of GPT-4o mini

[@code4AI]

Genius, I know. In the last example, after all the GPT-4o MINI, I choose to show the big brother GPT-4o, as comparison. Just perfect service. 😂

[@mirek190]

really cool comparison!

[@slm6873]

Unconfirmed but 4o-mini appears to be using 4o for images, that's why it costs the exact same (for images, incl. total cost of tokens/tile) on OAI API.