OpenAI's flagship image generation and editing model, built directly into the GPT-5 architecture to provide faster, more precise, and production-ready visual generation. It serves as a significant upgrade over previous models, focusing on "region-aware editing"—the ability to modify specific parts of an image without changing the entire scene
One POST request. Get the result back directly — as an image, video, or JSON depending on the tool.
curl -X POST https://apiai.me/api/workflow/openai-gpt-image-15 \
-H "X-API-Key: YOUR_API_KEY" \
-F "image=@input.jpg" \
-F "background=transparent" \
-F "frequency_penalty=VALUE" \
-F "input_fidelity=high" \
-F "max_tokens=VALUE" \
-F "output_format=png" \
-F "presence_penalty=VALUE" \
-F "PROMPT=VALUE" \
-F "quality=standard" \
-F "size=1024x1024" \
-F "style=vivid" \
-F "temperature=0" \
-F "top_p=0"
--output result.png
Test this tool visually before writing any code. Upload an image, set parameters, and see the result live. When it looks right, copy the auto-generated curl command and paste it into your app.
Process hundreds of images at once without writing a loop. Upload a CSV with one row per item, set your parameters, and download the results as a ZIP when they're done.
| Name | Required | Description | Default / Options |
|---|---|---|---|
background |
optional | Background transparency (gpt-image-1/1.5 only): transparent, opaque, auto | transparentopaqueauto
|
frequency_penalty |
optional | Reduce repetition of token sequences (-2 to 2) | — |
input_fidelity |
optional | Input image fidelity for /images/edits (gpt-image models only): high preserves original closely, low gives more creative freedom | highlow
|
max_tokens |
optional | Maximum number of tokens to generate | — |
output_format |
optional | Output format (gpt-image-1/1.5/mini only): png, webp, or jpeg | pngwebpjpeg
|
presence_penalty |
optional | Encourage discussion of new topics (-2 to 2) | — |
PROMPT |
required | Text prompt for the OpenAI model | — |
quality |
optional | Image quality. dall-e-3: standard, hd. gpt-image-1/1.5: low, medium, high, auto | standardhdlowmediumhighauto
|
size |
optional | Output image size. gpt-image-1/1.5: 1024x1024, 1536x1024, 1024x1536, auto. dall-e-3: 1024x1024, 1792x1024, 1024x1792 | 1024x10241536x10241024x15361792x10241024x1792auto
|
style |
optional | Image style (dall-e-3 only): vivid (hyper-real) or natural (less hyper-real) | vividnatural
|
temperature |
optional | Sampling temperature (0-2). Higher = more creative, lower = more deterministic | 012
|
top_p |
optional | Nucleus sampling: cumulative probability cutoff (0-1) | 01
|
Get an API key, test OpenAI GPT image 1.5 in the dashboard, and copy the curl command.