Image model API
GPT Image 2 5 Sunburst API
GPT Image 2.5 Sunburst is OpenAI’s high-end image generation and editing model, with the Sunburst variant specifically optimized for workflows where editing precision and controlled visual refinement matter most. It can transform reference images according to detailed prompts while preserving important elements of the original composition. The Kie.ai image-to-image implementation supports up to 16 input images, resolutions from 1K to 4K, flexible aspect ratios, and transparent or opaque backgrounds. This makes it suitable for sophisticated image editing, multi-reference composition, product v
- Model id
gpt-image-2-5-sunburst-1- Takes
- Text (required)
- Makes
- Image
- Endpoint
POST /api/v1/images/generations- Made by
- OpenAI
- Mode
- Async (job polling)
Call GPT Image 2 5 Sunburst
https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.Model gpt-image-2-5-sunburst-1
POST /api/v1/images/generationsasync · poll /v1/jobs/:id
curl https://payload.rentprompts.com/api/v1/images/generations \
-H "Authorization: Bearer rp_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2-5-sunburst-1",
"prompt": "A lighthouse at dusk, watercolor",
"n": 1
}'
# Async models answer HTTP 202 with a job. Poll it until status is
# "succeeded" (output.url / output.urls) or "failed" (error):
curl https://payload.rentprompts.com/api/v1/jobs/JOB_ID \
-H "Authorization: Bearer rp_live_YOUR_KEY"Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →
What a typical call costs
- 1 image4 Joules
- 4 images16 Joules
Send requests to POST /api/v1/images/generations. GPT Image 2 5 Sunburst runs asynchronously: the request answers HTTP 202 with a job, and you poll GET /api/v1/jobs/{id} until the result is ready.