Prompt/Message Counter — Track Rate Limiting in ChatGPT

David Such
9 min readJan 7, 2024

In late November 2023, OpenAI started to rate limit ChatGPT. This was just after the first OpenAI DevDay (Nov 6th), which drove an explosion of activity as users rushed to find out about the new GPT Store. If you want to track usage rate limits, prompt/message numbers and tokens, uploaded file size, session duration, chat.openai.com status, ping times and latency, then you need the Reefwing Session Statistics GPT.

Figure 1. Statistical Distribution [Image Credit: Midjourney]

When developing a custom GPT in GPT Builder, you will quickly hit the rate limit when iterating on Instruction prompts or actions. We were recently testing a spell checking GPT, and hit the usage cap in just over half an hour (Figure 2).

Figure 2. The dreaded ChatGPT Rate Limit Message

ChatGPT is not overly transparent about the usage cap calculation and it seems to change depending on the traffic being experienced. We suspect that ChatGPT is working hard at increasing its infrastructure, which is expensive.

Figure 3. Chrome DevTools

OpenAI does leave some breadcrumbs in the network traffic, which we can follow, to find out what…

--

--

David Such
David Such

Written by David Such

Reefwing Software · Embedded Systems Engineer · iOS & AI Development · Robotics · Drones · Arduino · Raspberry Pi · Flight Control

No responses yet