Hi
How are the costs of Gemini Vertex AI calls calculated? Are you using the pricing mentioned in https://cloud.google.com/vertex-ai/generative-ai/pricing?
I see that the costs in portkey logs are higher than what I see in GCP billing reports.

I've been facing an issue from the past few weeks where some of my requests end up in a connection error. But I see those requests in https://app.portkey.ai/organisation/org-uuid/logs

I see isQuotaExceeded : false in one of portkey's api calls.

Any suggestions?

Hey, one more issue on playground for Vertex AI multimodal models - There's no input for image data in pretty view.
I can still provide image data in json view, but all the text content is going to be in one line which makes it hard to read.