Maximum Context token for Tuned Models via API Calls

Gemini API
, ,
1

I understand that the context tokens for Gemini Tuned Models via the AI Studio is roughly 16k tokens. Is this the same as when calling via an API? I’m having trouble locating the documentation for that (if any).

1 Like
3

Hi @Joseph_Nwodo ,
Yes it is same.
Refer Documentation:
Generate content with the Gemini API in Vertex AI | Generative AI on Vertex AI | Google Cloud
Thanks!