# GPT4 OCR/Image Recognition

**URL:** <https://community.openai.com/t/gpt4-ocr-image-recognition/439478>\
**Category:** API\
**Tags:** gpt-4\
**Created:** [October 18, 2023, 4:42pm UTC](https://community.openai.com/t/gpt4-ocr-image-recognition/439478 "2023-10-18T16:42:56Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![info90](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/info90/32/222421_2.png) [@info90](https://community.openai.com/u/info90)\
**Post date:** [October 18, 2023, 4:42pm UTC](https://community.openai.com/t/gpt4-ocr-image-recognition/439478/1 "2023-10-18T16:42:56Z")

</div>

Dear Reader, For a few weeks now, it has been possible to use GPT-4(V) visual. It seems like an alternative to OCR, or maybe it is OCR. Is it possible to use this functionality with my GPT-4 API??

---

<div class="post-metadata">

**Author:** ![Diet](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/diet/32/562749_2.png) [@Diet](https://community.openai.com/u/Diet)\
**Post date:** [October 18, 2023, 5:43pm UTC](https://community.openai.com/t/gpt4-ocr-image-recognition/439478/2 "2023-10-18T17:43:53Z")

</div>

Unfortunately we haven’t heard anything regarding vision on the API.

I’d be super interested to see how they will handle billing.

That said, I don’t think it will be a drop-in replacement for OCR at this point. these LMMs are pretty inattentive readers, although that could maybe be overcome agentically.

---

<div class="post-metadata">

**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\
**Post date:** [October 18, 2023, 5:50pm UTC](https://community.openai.com/t/gpt4-ocr-image-recognition/439478/3 "2023-10-18T17:50:43Z")

</div>

GPT-4 has been trained to refuse outright OCR requests, although you can see its skill in reading when you work around this. However, there is OCR software that doesn’t take a quarter-million-dollar stack of servers to save you typing in a page.

---

<div class="post-metadata">

**Author:** ![EricGT](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ericgt/32/20571_2.png) [@EricGT](https://community.openai.com/u/EricGT)\
**Post date:** [December 18, 2023, 9:34am UTC](https://community.openai.com/t/gpt4-ocr-image-recognition/439478/4 "2023-12-18T09:34:25Z")

</div>

Closed on December 18, 2023, 9:34am UTC


