I have added credentials for both open AI and anthropic but there is no change with regards to the credits being used. I’m still getting the same credit usage as if I had not entered in my API credentials. I have made sure that the models being used are either open AI or anthropic.
Hey @Thomas_Walker! If you’re reporting an issue with a flow or an error in a run, please include the run link and make sure it’s shareable so we can take a look.
-
Find your run link on the history page. Format:
https://www.gumloop.com/pipeline?run_id={{your_run_id}}&workbook_id={{workbook_id}} -
Make it shareable by clicking “Share” → ‘Anyone with the link can view’ in the top-left corner of the flow screen.
-
Provide details about the issue—more context helps us troubleshoot faster.
You can find your run history here: https://www.gumloop.com/history
Hey @Thomas_Walker – Can you share the run link please? You can find the run link on the https://www.gumloop.com/history page or through the Previous Runs tab on the canvas.
Also please share access by adding my email (wasay@gumloop.com) or setting the workbook to “anyone with the link can view” from the share button on the run link.
Hi Wasay, thank you, here is the link:
https://www.gumloop.com/pipeline?run_id=4f7GYT5LxV29BFgEcMj5o7&workbook_id=iXybhmVggZiucDQAQDfj6q
Hi Wasay, seems like this closed over the easter weekend, can you help with this request?
Hey @Thomas_Walker – Apologies, missed the earlier notification.
We deprecated GPT 4o-mini for GPT 4.1-mini, if you delete and add back the Ask AI and the Extract Data nodes you should be all set. If you still run into any issues please share the run link here and we’ll get it sorted for you.
Also, can you double check if the OpenAI credentials are properly added in Gumloop | Settings?
Hi Wasay
Ok, I did as you said, removed the ask ai and extract data nodes and then re-added them. I see that the model info has been updated.
I now have another issue, it seems that my error shield is now being triggered with the problem stated that the urls are not valid. I have not changed the test urls and they dont trigger the error shield on the original flow.
https://www.gumloop.com/pipeline?run_id=Z482MsVdAs4mj2ZcLdLArU&workbook_id=1G7jUP2L27aH2MvjLpgqeC
Here is the updated workbook:
Hey @Thomas_Walker – Could you save the latest workflow and please share access by adding my email or setting the workbook to “anyone with the link can view” from the share button on the run link.
The run link for the updated workflow would be super helpful too so I can view the inputs/outputs please? You can find the run link on the https://www.gumloop.com/history page or through the Previous Runs tab on the canvas.
I have changed the settings to allow anyone with the link. Please send me your email and I will share it from there too.
I have copied the workbook link but it doesn’t seem right? https://www.gumloop.com/hub?tab=1
Thank you!
I now have another issue, it seems that my error shield is now being triggered with the problem stated that the urls are not valid. I have not changed the test urls and they dont trigger the error shield on the original flow.
The reason why this run failed is because the output node in the subflow Outreach Message is not defined. Once you fix that you should be all set. Problematic Subflow Link.
If you’re curious how I figured this out, I just expanded each run from the run log and followed the trail. I’d also recommend giving this a quick read—it’s really helpful for debugging flows and checking outputs from the run log: Run Log Doc.
Let me know if that clears things up or if there’s anything else I might’ve missed.
1 Like
Ok, thanks Wasay but there has been absolutely no change to the amount of credits being used even after following all your instructions.
It’s costing me over 68 credits for each instance of this flow
I see, thanks for flagging! Could you share the latest run please?
Also, just to make sure you’ve added the API keys on the credentials page here right:
cc: @rahul-gumloop OpenAI/Anthropic API key not being utilized for this user.
The OpenAI/Anthropic API key is being used, that’s why the credits for those nodes are 1.
The vast majority (60) of credits being used in your flow are for the “Enrich” nodes, which use services like Apollo, ProxyCurl, and Hunter.io to get information. Unless you have API key those, 60 credits will be used every time that node is run.
You can see a credit breakdown per node in the run logs on the right hand side.
1 Like
This topic was automatically closed 60 minutes after the last reply. New replies are no longer allowed.