Skip to content

Document multipart model handling for image edits #896

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
akhilmmenon wants to merge 9 commits into
base: main
Choose a base branch
from
+24 −1
Open

Document multipart model handling for image edits #896

Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
5cb92fd
Update Azure-OpenAI docs to include Image Editing section
Apr 29, 2026
8329642
Added runnable version of the code
Apr 29, 2026
4422b20
Made this change provider agnostic
Apr 29, 2026
0bb946d
Update product/ai-gateway/multimodal-capabilities/image-generation.mdx
akhilmmenon Apr 29, 2026
e682f9e
Update product/ai-gateway/multimodal-capabilities/image-generation.mdx
akhilmmenon Apr 29, 2026
25385df
Modified the note for image edit in image-generation.mdx and create-i…
akhilmmenon May 15, 2026
4649c0b
Applied the changes recommended
akhilmmenon May 18, 2026
4657e48
Removed the end note as the content was being redundant
akhilmmenon May 18, 2026
fe0bd10
Modified the Image Editing intro
May 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 24 additions & 1 deletion product/ai-gateway/multimodal-capabilities/image-generation.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,9 +125,32 @@ curl "https://api.portkey.ai/v1/images/generations" \
</Tab>
</Tabs>

## Image Editing

Portkey supports the OpenAI signature to make image edit requests using multipart form data.

```python

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY", provider="openai")
with open("image.png", "rb") as image_file:
image = portkey.images.edit(
model="gpt-image-2",
prompt="Add snow",
image=[("image.png", image_file.read(), "image/png")],
size="1024x1024",
)
```

<Note>
Image edit models currently do not support provider-prefixed model slugs in the request body. Pass the provider in headers and keep `model` as the raw provider model name.
</Note>

### API Reference

[Create Image](/provider-endpoints/images/create-image)
- [Create Image](/provider-endpoints/images/create-image)
- [Create Image Edit](/provider-endpoints/images/create-image-edit)

### OpenAI gpt-image-1 Parameters

Expand Down