#ChatGPT Analyzing Photos

1 messages · Page 1 of 1 (latest)

marble steppe
#

Hi does anyone know when setting up the chat completions endpoint locally if I can attach an image to the input message to have ChatGPT analyze the photo and return a response about the photo? If so is this only applicable to GPT-4 models or can I run this with gpt-3.5?

gray shaleBOT
#

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

#

Yes, you can use the Chat Completions API to have ChatGPT analyze photos. This feature is available with the GPT-4 model. To use this feature, you need to ensure the model selector is set to GPT-4 and then add the image inputs[^1^].

This feature was introduced with the release of GPT-4 Turbo at OpenAI developer day in November 2023[^2^]. You can find more details about this feature in the vision developer guide[^2^].

Unfortunately, this feature is not available for the gpt-3.5 model[^1^].

^1^]: [Image inputs for ChatGPT - FAQ (https://help.openai.com/en/articles/8400551-image-inputs-for-chatgpt-faq)
^2^]: [How can I use GPT-4 with images? (https://help.openai.com/en/articles/7127995-how-can-i-use-gpt-4-with-images)

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

#

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