Public Versions and Endpoints
| Model ID | Endpoints | Price | Catalog |
|---|---|---|---|
gpt-image-2
|
/api/v1/gpt_image_2/text_to_image
/api/v1/gpt_image_2/edit_image
|
$0.06 / call | Model detail |
Verify
Poll until the task reaches a terminal status
POST /api/v1/gpt_image_2/text_to_image and save the returned Task id.
GET /api/v1/gpt_image_2/text_to_image/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.Configuration
Guide endpoint: /api/v1/gpt_image_2/text_to_image
export RUNAPI_API_KEY=your_api_key
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2",
"prompt": "A cobalt vase on white marble."
}'Get Started in 3 Steps
-
Choose a model ID
Select a public catalog model ID and review its endpoint and current starting price.
-
Configure RunAPI
Set RUNAPI_API_KEY before making the endpoint request.
-
Verify the result
For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.
What to Build with OpenClaw + GPT Image 2
-
UI mockups and app wireframes
Generate detailed UI mockups from written descriptions, including buttons, navigation, and placeholder content that reads correctly.
-
Text-heavy posters and presentations
Create posters, infographics, and slides where the exact text is given in the prompt and rendered with clean layouts.
-
Character design sheets
Generate character sheets with turnaround views from a single description, keeping features consistent across angles.
Why Use GPT Image 2 Through RunAPI + OpenClaw
-
1 variants, one API key
Use one RunAPI connection to choose among the live model variants without changing your integration.
-
Clear usage pricing
See current catalog pricing before you send a request, with no subscription or minimum spend required.
-
Automatic task workflows
Submit, poll, and collect asynchronous results through a consistent task workflow without writing manual polling code.
OpenClaw + GPT Image 2 Questions
Can I use GPT Image 2 in OpenClaw?
Yes. OpenClaw agents call GPT Image 2 through the RunAPI endpoints shown on this page, with the same RunAPI API key used for chat. No extra skills or plugins are required.
Which aspect ratios and resolutions does GPT Image 2 support?
Set aspect_ratio to auto or a ratio from 1:1 to 21:9 or 9:21, and output_resolution to 1k, 2k, or 4k. Resolution defaults to 1k.
Can I edit an existing image with GPT Image 2?
Yes. Use the edit endpoint, pass the source images, and describe the change in natural language, such as replacing the background or adding an object.
Which model ID should I use?
Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.
Does this guide configure a chat model?
No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.