Chatgpt-4o-latest (500,000 TPM) dont work

[KromTon]

Bug Description

Problem: I connected the OpenAI node chatgpt-4o-latest, set the prompt: Translate text. The length of the input context is 33-35k tokens, the length of the context chatgpt-4o-latest (500,000TPM), but n8n returns an error at the output of the problem: The limit of 30,000TPM of the GPT-4o model has been exceeded. (At the same time, the API balance has been replenished, the limit for the model is indicated correctly on the website in the Limits section (Plan: Plus)) Why does n8n return the wrong model that was selected and an error of exceeded TPM? I contacted OpenAI and they confirmed the error on the n8n side, since I have access to the context onk of 500,000 for the chatgpt-4o-latest model, which is confirmed in my profile in the Limits section.

My n8n plan: Free (Trial)

n8n version: 1.94.1
Launch n8n via n8n Cloud
Operating system: Windows 10

To Reproduce

Problem: I connected the OpenAI node chatgpt-4o-latest, set the prompt: Translate text. The length of the input context is 33-35k tokens, the length of the context chatgpt-4o-latest (500,000TPM), but n8n returns an error at the output of the problem: The limit of 30,000TPM of the GPT-4o model has been exceeded. (At the same time, the API balance has been replenished, the limit for the model is indicated correctly on the website in the Limits section (Plan: Plus)) Why does n8n return the wrong model that was selected and an error of exceeded TPM? I contacted OpenAI and they confirmed the error on the n8n side, since I have access to the context onk of 500,000 for the chatgpt-4o-latest model, which is confirmed in my profile in the Limits section.

Expected behavior

How fix it?

Operating System

Windows 10

n8n Version

1.94.1

Node.js Version

22.15.1

Database

SQLite (default)

Execution mode

main (default)

[Joffcom]

Hey @KromTon,

We have created an internal ticket to look into this which we will be tracking as "GHC-2280"

[mpetit971]

I have the same concern