openai
* This model's size is not published. The figure is the exact midpoint of the reported range 20B–175B · confidence: leaked .
A Microsoft paper listed 20B and then retracted the detail; 175B is the GPT-3 davinci lineage it may descend from. The spread is the honest state of the evidence.
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...
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.