This 0.81 cents for 2k token is not right. claude api doens't cost this much. i think it's a bug

Hello, i found this two bugs. correct me if i am wrong

1. when i select gemini flash 2 model in portkey i am not able to attach images with it but flash model supports image funcnility. I am migrating from sonnet to gemini so i need this feature.

1. Portkey is showing two flash model and i am not sure what is the difference, i think there is only one model available right now.

Thanks

I am getting an error, but I don’t think I have more than 10k logs in January. It seems like the system is calculating the total logs instead.

Even if it’s calculating total logs, I should still have access to the 10k free logs, and the extra logs should be paid. That’s what the error message says (please check the screenshot).

How do i use prompt-catching with port-key and bedrock. This catch control setting is not available when i choose bedrock.

https://portkey.ai/docs/integrations/llms/anthropic/prompt-caching

I’m using Sonnet v2 with AWS Bedrock in the us-east-1 region. It seems that invocation is only supported with an inference profile for Sonnet v2, and I need to set this as the model ID: us.anthropic.claude-3-5-sonnet-20241022-v2:0.

However, in Portkey, all the model IDs start with anthropic.XXX instead of us.XXX. How do I configure portkey with inference profile.

Hi, I am facing an issue while uploading an image through portkey. So right now I am trying to pass two different image one image is 90 KB and another image is 790 KB. Whenever I pass 90 KB image, I am getting the response successfully but Whenever I pass 790 KB image I am getting the above error.

I tried both of these image in anthropic console and its working there. One issue can happen is that I am using the online base 64 image encoder maybe it could be causing the issue but again I am also encoding 90 KB image there and it is working.(https://www.base64-image.de/)

After trying few times i started gettign response under 6 seconds but it is unrelible. Some calls are still taking 15 seconds some are completing under 5 seconds. All the calls have same data and it is not hitting the catch

this feedback inside logs is in random order. not sure if that's a bug or intensional. but i think showing this logs in most recent first order would be more user friendly.

i think it's helpful if i can customise this column. I don't need Model name or path here as it will going to be same in my application. I want to display promptId here.
If i can configure this columns and order of the column then it would make this dashboard more user friendly.

I have one question regarding feedback.

Right now i am creating feedback using this code

const feedback = await portkey.feedback.create({ traceID: "test-trace-id", value: 6, weight: 2, })

if i call this code 4 times with same trace id then i can see 4 different values

I my application i have upvote and downvote button. If user upvote generation and then downvote then last upvote should be replaced with the downvote so i can see it properly in analytics.
In portkey i am not able to replace the previous feedback. It is just adding it stack and considering all the values when i check the graphs.

How do i handle this scenario.