Skip to main content

Get Support
Have a question? Let's get you an answer!

How Do I...? Troubleshooting Code & Webhooks Developer Zone

Other Help Resources
Wait, there's more! Check out these Community sourced spaces for additional resources.

Zapier Help Center Hire an Expert

Learning Resources
All of our best learning resources can be found here.

Featured Articles Show & Tell Zapier's products AI Hub Zapier Tools Hub

Share your knowledge
Give back to the Community by sharing your automation wins and helping to answer questions.

Share your success See unanswered questions User Groups

Other Learning Resources
Some of our favorite additional ways to upskill your Zapier knowledge.

Zapier Learn Zapier Blog Zapier Webinars

Product Updates
Check out what is new and upcoming with Zapier with our regular product updates.

Product Updates

Early Access Program
Want to join Early Access? Learn more here.

This post was split from the topic: 

​@SamB 

Thanks for the clarification! That makes sense about the TPM limit.

At this point I’m no longer running into TPM issues since my OpenAI tier has been upgraded, but now I’ve hit a different problem:

  • Until yesterday, Deep Research was running fine with o3-deep-research.

  • Suddenly, it no longer produces any output. Zap history shows no errors, just “delayed.”

  • If I use o4-mini-deep-research with max_output_tokens set to ~70,000, it works as expected.

  • But with o3-deep-research, nothing comes back at all — no error messages, just delayed indefinitely.

Has anyone else run into this behavior with o3-deep-research on Zapier? Or does anyone know of a workaround / solution?

Hey ​@Rei 👋 Hope you don’t mind but I moved your reply out into a new topic so we can address this different issue separately. 

The 04-mini-deep-research model is a faster model than the o3-deep-research model, so it’s possible that it’s just being too slow to respond and is timing out. But rather than surfacing a timeout error, it’s left stuck in that “Delayed” status - could be that there’s a bug that’s preventing the error from surfacing as it normally would. 🤔

I can see you reached out to our Support team and they’ve have reached out to our engineers about this. Which is perfect, they’ll be able to help get to the bottom of what’s causing those Zap runs to get stuck.

In the meantime, I’d suggest using the 04-mini-deep-research model instead since that’s faster and more cost affective model than the older o3 model.

Please do keep us updated on how it goes with our Support team, curious to know what they find!

​@SamB 
Thanks for the suggestion! 🙏

Just to summarize for others who might be running into the same issue:
Zapier uses a resumption process internally – it sends the request to OpenAI, generates a callback URL, and then waits for the response to resume the Zap run.

The problem here seems to be that the o3-deep-research response takes longer than the time Zapier is willing to wait, so Zapier times out first. That leaves the Zap stuck in the “Waiting/Delayed” state instead of surfacing a proper timeout error(It seems this is typical problem).

Will keep this thread updated once I hear back from Support/Engineering!

Sorry for the delay in my reply here ​@Rei. Thank you so much for sharing that summary here for folks - it’s super helpful. 🤗

Looking forward to hearing how it goes with the Support/Engineering teams! 

Terms & ConditionsAccessibility statement