#GPT-4o

1 messages · Page 1 of 1 (latest)

plush stirrupBOT
#

Hi @north socket. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

The context window for GPT-4o is 128,000 tokens. This is the maximum number of tokens from the input that the model considers when generating an output. However, it's important to note that the max_tokens parameter, which sets the limit to how many tokens the model will output at one time, has a limit of 4096 tokens. This is the case for most models, not just OpenAI's, and there is no parameter to adjust the context window of the model itself source (https://community.openai.com/t/761439).

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@north socket kapa.ai is still learning and improving, please let us know how it did by reacting below

north socket
#

@plush stirrup what is the context limit for free users of GPT-4o?

plush stirrupBOT
#

Let me check the knowledge base for you. One moment! :books:

#

The specific context limit for free users of GPT-4o is not explicitly mentioned in the provided knowledge sources. However, it's mentioned that the usage for free users is 1/5 the usage of plus and can be adjusted dynamically based on load source (https://community.openai.com/t/774719). For more detailed information, you may want to refer to OpenAI's official documentation or support.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: