I am using an edited form of the Wordpress GPT content creator flow. Inside the loop, I have a delay for 2 minutes to avoid any time outs. The chat GPT is set for 4o. Below is the question
“1. New Row values B” Write the content of the section titled " " 4. Loop on Items . You must adhere to these guidelines:
Use metaphors and illustrations to help bring the topic to life.
Write in the style of Noami Carr and Pete Walker.
Keep all titles and subheadings short and simple.
Keep the reading level at the 10th grade reading level.
Avoid passive voice.
Break up any sentence greater than 19 words.
“1 New Row values E”
This section is part of a bigger article called "3. Code title ". Don’t include the title in your output. Use a variation " 1. New Row values D " of in your content, only include the paragraph content. Don’t create a summary or conclusion paragraph. Use html tags for subheadings, create enough levels of subheadings to get the point across, which is (h3). You can create two or three of these h3 subheadings. Don’t make the subheadings sound too similar to the original section title provided to you.
Temp: 1
Max Token: 4096
Top P: 1
Frequency Request: 0
Presence Penalty: .6
Memory: “”
I get to the 5th loop and the system stops with the error
“429 Request too large for gpt-4o in organization org-token on tokens per min (TPM): Limit 30000, Requested 233316. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.”
Is this due to the number of times it runs? Or is there something else I can do? I know the default had 5. This method can have 3 to 10 sometimes.
Edit: Digging deeper, Rate limits - OpenAI API
I am using the Tier 1. on 4o. So I am trying to figure out why it would stop me at the 5th loop. Any ideas would help. Thank you.