I have been using chat gpt for a long time, and sometimes after a certain amoun tof time, even if I have sent like only 3 messages in a few minutes, they give me the Too many requests in 1 hour, what does i tmean? How many messages can I send in 1 hour. I use Chat GPT 3 How long do I have to wait, before I can send another response?
#CHAT GPT 3 limit
1 messages · Page 1 of 1 (latest)
Hi @carmine wedge. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
The rate limits for the ChatGPT API depend on the type of user you are. If you are a free trial user, the rate limits are 20 requests per minute (RPM) and 40,000 tokens per minute (TPM). For pay-as-you-go users in the first 48 hours, the limits are 60 RPM and 60,000 TPM. After 48 hours, the limits increase to 3,500 RPM and 90,000 TPM source (https://help.openai.com/en/articles/7232945-how-can-i-use-the-chatgpt-api).
If you're exceeding these limits, you'll receive a 429 response code, indicating that you've hit the rate limit. The API will respect these response codes and dynamically back off from sending requests to your plugin after receiving a certain number of 429's or 500's in a short period of time source (https://platform.openai.com/docs/plugins/production).
If you're using GPT-4 in ChatGPT, there's a cap of 50 messages every 3 hours. After this, you will have to wait for your quota to reset source (https://help.openai.com/en/articles/7127997-how-can-i-use-gpt-4-in-chatgpt).
Remember that both input and output tokens count toward these quantities. For example, if your API call used 10 tokens in the message input and you received 20 tokens in the message output, you would be billed for 30 tokens source (https://platform.openai.com/docs/guides/text-generation).
If you're still encountering issues, it might be worth checking your usage in your OpenAI account or reaching out to OpenAI support for further assistance.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
@carmine wedge kapa.ai is still learning and improving, please let us know how it did by reacting below