Public Versions and Endpoints
| Model ID | Endpoints | Price | Catalog |
|---|---|---|---|
gpt-image-1.5
|
/api/v1/gpt_image/edit_image
/api/v1/gpt_image/text_to_image
|
$0.12 / call | Model detail |
Verify
Poll until the task reaches a terminal status
POST /api/v1/gpt_image/text_to_image and save the returned Task id.
GET /api/v1/gpt_image/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/text_to_image
export RUNAPI_API_KEY=your_api_key
curl -X POST https://runapi.ai/api/v1/gpt_image/text_to_image \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-1.5",
"prompt": "A cobalt vase on white marble.",
"aspect_ratio": "1:1",
"quality": "high"
}'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 Hermes Agent + GPT Image
-
Marketing and product visuals
Generate campaign images, product shots, and social creatives from a written brief.
-
Batch creative variations
Produce many versions of a concept in one run to compare styles, layouts, and formats.
-
Editing and inpainting
Refine an existing image by describing changes to its background, objects, or details where the model offers editing endpoints.
Why Use GPT Image Through RunAPI + Hermes Agent
-
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.
Hermes Agent + GPT Image Questions
What endpoints does GPT Image support?
Text-to-image and image editing. Both accept detailed text prompts with compositional instructions.
How does compositional control work?
GPT Image follows spatial layout instructions in your prompt — you can specify where objects appear, relative sizes, and arrangement within the frame.
What output sizes are available?
3 fixed sizes up to 1536 pixels.
How does GPT Image compare to GPT Image 2?
GPT Image 2 is the newer model with near-perfect multilingual text rendering and up to 4K output. GPT Image is the prior generation with strong compositional control.
Can I use GPT Image for editing?
Yes — the image editing endpoint accepts a source image and modifies it based on your text prompt, acting as an image editing tool.
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.