openai
* This model's size is not published. The figure is the exact midpoint of the reported range 111B–200B · confidence: speculation .
111B is a conservative lower bound measured from text memorization; 200B is an independent estimate from GPU cost, itself stated as possibly off by 2x.
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more here . GPT-4o ("o" for "omni") is...
The OpenRouter API truncates descriptions — read the full text at the source
Every id and name this model has been seen under — for matching it against another catalogue.