# Gpt-4-vision-preview "can't process images input?"

**URL:** <https://community.openai.com/t/gpt-4-vision-preview-cant-process-images-input/492192>\
**Category:** API\
**Tags:** gpt-4, api\
**Created:** [November 10, 2023, 9:09am UTC](https://community.openai.com/t/gpt-4-vision-preview-cant-process-images-input/492192 "2023-11-10T09:09:04Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![neverbeangrydanama](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/neverbeangrydanama/32/149195_2.png) [@neverbeangrydanama](https://community.openai.com/u/neverbeangrydanama)\
**Post date:** [November 10, 2023, 9:09am UTC](https://community.openai.com/t/gpt-4-vision-preview-cant-process-images-input/492192/1 "2023-11-10T09:09:04Z")

</div>

why model “gpt-4-vision-preview” can not process images input? It replys: “I’m sorry, but as a language model AI, I do not have the capability to view images or videos.” But I do set the model parameter as “gpt-4-vision-preview” in the code.

---

<div class="post-metadata">

**Author:** ![HenriqueMelo](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/henriquemelo/32/255626_2.png) [@HenriqueMelo](https://community.openai.com/u/HenriqueMelo)\
**Post date:** [November 20, 2023, 4:52pm UTC](https://community.openai.com/t/gpt-4-vision-preview-cant-process-images-input/492192/2 "2023-11-20T16:52:41Z")

</div>

Hi and welcome to the Developer Forum!

There are typically two reasons for issues with this problem.  
First, check the ‘max\_tokens’ property. It must be adequate for both your prompt and the image. Refer to the OpenAI documentation for guidance on calculating tokens ([https://platform.openai.com/docs/guides/vision/calculating-costs](https://platform.openai.com/docs/guides/vision/calculating-costs)).

Second, the structure of your request could be the issue (It happened to me). Errors often occur with incorrect request formats. I recommend reviewing the request structure guidelines in the OpenAI documentation for a better understanding ([https://platform.openai.com/docs/guides/vision/quick-start](https://platform.openai.com/docs/guides/vision/quick-start)).