What Does BrowserAct ChatGPT Image 2.5 API Do?
This template cannot be run directly. Create an editable duplicate in your workspace, restore your ChatGPT login through Improve, publish the copied Bot, and then run or call your personal Bot.
Turn your own logged-in ChatGPT Image 2.5 subscription into a reusable BrowserAct Bot. Submit an image prompt and optional reference images, then receive a downloadable PNG result for image generation or editing.
This is not the official OpenAI API. The copied Bot automates the ChatGPT web experience through your own authenticated browser profile and can be invoked through the BrowserAct API or MCP after you publish it.
Key Features
- Uses your own logged-in ChatGPT Image 2.5 subscription.
- Supports text-to-image generation and image-to-image editing.
- Accepts an image prompt and up to four reference images.
- Returns the generated PNG file and structured result metadata.
- Lets your published copy run through BrowserAct API, MCP, or automation tools.
Input Parameters
| Parameter | Configuration |
|---|---|
prompt | String · Required Default: Create a cinematic product photo of a transparent glass perfume bottle on dark green stoneDescribe the image to generate or the edit to apply. |
reference_images | Image list · Optional Default: noneAdd up to four reference images when editing or guiding the result. |
max_prompt_characters | Integer · Required Default: 4000Maximum accepted prompt length. |
max_reference_images | Integer · Required Default: 4Maximum reference-image count. |
max_reference_image_mb | Integer · Required Default: 10Maximum size for each reference image. |
Example Output
The table shows one real result from a completed image-editing run.
| Field | Result |
|---|---|
image_file | generated-image-1.png |
image_format | png |
image_bytes | 2408988 |
image_public_url | null |
mode | image-to-image |
prompt | Replace the background with a dark studio scene while preserving the subject. |
How Does It Work?
- You create an editable duplicate and restore your own ChatGPT login in the copied Bot.
- The run checks the prompt and optional reference-image limits.
- The Bot opens the logged-in ChatGPT image experience and submits the request.
- For editing, it uploads the supplied reference images before submitting the prompt.
- The Bot waits for image generation to finish, downloads the PNG, and returns the file metadata.
Create Your Own ChatGPT Image 2.5 API Bot
- Click Create Editable Duplicate in the upper-right corner to save the Bot to your workspace.
- Open the copied Bot, go to Build, and select Improve.
- Enter:
My login session is no longer available. I need to log in again. Do not rebuild or refactor the Bot. Keep the existing workflow, inputs, and outputs unchanged. - Complete ChatGPT login in your Browser Profile, return control to Improve, and publish the copied Bot.
- Run the Bot from BrowserAct or call the published Bot through the BrowserAct API or MCP using its Bot ID.
Automation and Export
After publishing your duplicate, use its Bot ID with the BrowserAct API, connect it to MCP-based agents, or route generated files through n8n, Make, Zapier, and your own applications.
Need Help?
Need help restoring the login session or connecting your copied Bot?
