Hi @dreamy ridge. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
#Is there rate limit/ usage limit ( not message limit or message cap) for chatgpt ( not api)
fringe whaleBOT
Based on the information provided in the extracts, there is no specific mention of a rate limit or usage limit for the ChatGPT service outside of the API. However, it's important to note that for ChatGPT Plus subscribers, GPT-4 access on chat.openai.com comes with a usage cap. The exact usage cap is dynamically adjusted depending on demand and system performance in practice. Currently, GPT-4 has a cap of 50 messages every 3 hours source (https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4).
Please note that this does not provide subscribers with access to the API. For API usage, there are specific rate limits and usage limits in place, which vary depending on the type of user (free trial, pay-as-you-go within the first 48 hours, and pay-as-you-go after 48 hours) source (https://help.openai.com/en/articles/5955598-is-api-usage-subject-to-any-rate-limits).
For more detailed information or updates, it's recommended to check OpenAI's official documentation or contact OpenAI support directly.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
dreamy ridge
@fringe whale What if someone uses chatgpt3.5 only? as a paid user? there are no message cap limits. but are there any kind of rate limits?
fringe whaleBOT
Let me check the knowledge base for you. One moment! :books:
Yes, there are rate limits for using the ChatGPT API, including the gpt-3.5-turbo model. These limits vary depending on the user's status:
- Free trial users: 20 requests per minute (RPM) and 40,000 tokens per minute (TPM)
- Pay-as-you-go users (first 48 hours): 60 RPM and 60,000 TPM
- Pay-as-you-go users (after 48 hours): 3500 RPM and 90,000 TPM
These limits are in place to ensure fair usage and system stability. If you exceed these limits, you may receive a 429 response code, indicating that you should reduce your request rate.
For more detailed information, please refer to the OpenAI API documentation (https://help.openai.com/en/articles/7232945-how-can-i-use-the-chatgpt-api).
Please note that these rate limits apply to API usage. If you're using the ChatGPT service outside of the API (for example, on chat.openai.com), different rules may apply. For the most accurate information, it's recommended to check OpenAI's official documentation or contact OpenAI support directly.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
dreamy ridge
@fringe whale how aobut chatgpt ( not api ) chat.openai.com
fringe whaleBOT
Let me check the knowledge base for you. One moment! :books:
Sorry @dreamy ridge, I am experiencing especially high traffic right now, please try again. :technologist:
dreamy ridge
ok dont worry
dreamy ridge
@fringe whale try again
fringe whaleBOT
Let me check the knowledge base for you. One moment! :books:
Based on the information provided in the extracts, there are indeed rate limits for the gpt-3.5-turbo model, which is part of the ChatGPT API. The rate limits vary depending on the user's status:
- Free trial users: 20 requests per minute (RPM) and 40,000 tokens per minute (TPM)
- Pay-as-you-go users (first 48 hours): 60 RPM and 60,000 TPM
- Pay-as-you-go users (after 48 hours): 3500 RPM and 90,000 TPM
These details are mentioned in the extract from the OpenAI Help Article (https://help.openai.com/en/articles/7232945-how-can-i-use-the-chatgpt-api).