Hey Support, I've been using openai to enrich lead data which has taken me from Usage Tier 1 to Usage Tier 4 very quickly that's cost me like $225 in openai... I still need to do more enrichment before the campain is finished but I'm unable to use openai integration. It's coming up with the error in clay "Could not finish the message because max_tokens or model output limit was reached. Please try again with higher max_tokens."
I have messaged openai support and the bot is responding with:
"Hi! I'm an AI support agent here to help.
The error message you’re getting—"Could not finish the message because max_tokens or model output limit was reached"—usually isn’t about credits or your usage tier. Instead, it means that either the prompt you (or Clay.com) are sending is too long, or the response you're asking for would go over the model’s output token limit.
Here’s how you can address this:
Try sending a shorter prompt or asking for a shorter response.
If possible on Clay.com, look for a “max_tokens” setting in your integration—set it to a higher value (but not above the model’s documented max).
Make sure that your overall prompt + expected output stay within the limits set for your usage tier and the model you are using (for most GPT-4 models, that’s usually 128k tokens, but check what’s available on Clay.com).
Your credits and tier affect how much you can use the API, but they do not increase the per-request token or output limit. If Clay.com’s platform has its own internal limits, you may need to reach out to their support to see if they allow changing max_tokens or if there are other platform-specific restrictions.
Let me know if you want details on per-model token limits, or need help finding these settings in your Clay.com workflow!"
I'm not sure where the problem lies or what I should do? Can you offer any help / guidance?
