#  GPT-Image-1 Model – Experiencing Delayed API Responses

**URL:** <https://community.openai.com/t/gpt-image-1-model-experiencing-delayed-api-responses/1322483>\
**Category:** Feedback\
**Tags:** gpt-4, chatgpt, api\
**Created:** [July 23, 2025, 8:53am UTC](https://community.openai.com/t/gpt-image-1-model-experiencing-delayed-api-responses/1322483 "2025-07-23T08:53:54Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Krishan\_Sharma](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/krishan_sharma/32/514700_2.png) [@Krishan\_Sharma](https://community.openai.com/u/Krishan_Sharma)\
**Post date:** [July 23, 2025, 8:53am UTC](https://community.openai.com/t/gpt-image-1-model-experiencing-delayed-api-responses/1322483/1 "2025-07-23T08:53:54Z")

</div>

Hi OpenAI Team,  
Just wanted to share feedback: I’m seeing consistently **slow response times** with the `gpt-image-1` model. It would be great if this could be optimized for better speed and user experience.

Thanks for your hard work!

---

<div class="post-metadata">

**Author:** ![VeitB](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/veitb/32/712987_2.png) [@VeitB](https://community.openai.com/u/VeitB)\
**Post date:** [July 23, 2025, 9:14am UTC](https://community.openai.com/t/gpt-image-1-model-experiencing-delayed-api-responses/1322483/2 "2025-07-23T09:14:50Z")

</div>

Hi and welcome to the community!

The new image generation model is not exactly the fastest and this can be the most simple explanation for the high latency you are observing. Then the question is if latency has been worse recently compared to before.

Alternatively you can look into the partial image streaming option that has recently been released. It’s more a ux feature because ultimately the image generation is not sped up but it can help to improve the experience.

> [@Introducing support for remote MCP servers, image generation, Code Interpreter, and more in the Responses API](https://community.openai.com/t/introducing-support-for-remote-mcp-servers-image-generation-code-interpreter-and-more-in-the-responses-api/1266973/32):
>
> Have you set the # of partial images? Streaming for images works a bit differently than text. You’ll need to define how many parts of the image (from top to bottom) should stream back, up to 3 parts. stream: true, tools: [{ type: "image\_generation", partial\_images: 3 }],

---

<div class="post-metadata">

**Author:** ![Krishan\_Sharma](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/krishan_sharma/32/514700_2.png) [@Krishan\_Sharma](https://community.openai.com/u/Krishan_Sharma)\
**Post date:** [July 23, 2025, 9:35am UTC](https://community.openai.com/t/gpt-image-1-model-experiencing-delayed-api-responses/1322483/3 "2025-07-23T09:35:57Z")

</div>

I’m using the `gpt-image-1` model to generate full images (not using streaming), and my tool isn’t publicly accessible. Here’s an example of a prompt I used:

> “A premium, vibrant product composition with a stylish partial table base visible under the product arrangement on the right side of the frame. … [rest of prompt]”

For this prompt, the image `generated_1753260705617.png` took **1m 43s** to generate:

✅ Image ‘generated\_1753260705617.png’ generated in 1m 43s.

```auto

I understand detailed prompts may require more time, but just wanted to share this as feedback regarding latency, in case it helps with further improvements.

Thanks!
```

---

<div class="post-metadata">

**Author:** ![VeitB](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/veitb/32/712987_2.png) [@VeitB](https://community.openai.com/u/VeitB)\
**Post date:** [July 23, 2025, 10:02am UTC](https://community.openai.com/t/gpt-image-1-model-experiencing-delayed-api-responses/1322483/4 "2025-07-23T10:02:28Z")

</div>

Yes, that sounds about right because currently image generation can [take up to two minutes.](https://platform.openai.com/docs/guides/image-generation#limitations)

Let’s hope that we will get a faster model with comparable quality soon!