Openai Gpt Image 1

Playground

OpenAI’s gpt-image-1 enables image generation and image editing via OpenAI’s image API, ideal for creating and refining images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

OpenAI GPT-Image-1

Edit and transform images with natural language using OpenAI’s GPT-Image-1. This versatile model understands your instructions to apply style changes, modifications, and creative transformations — with optional mask support for precise regional editing and multiple quality tiers to match your needs and budget.

Why It Looks Great

Natural language editing: Describe transformations in plain text — style changes, modifications, enhancements.
Mask support: Use mask images for precise control over which areas to edit.
Quality tiers: Choose from low, medium, or high quality based on your needs.
Multiple sizes: Output in square (1024x1024) or rectangular (1024x1536, 1536x1024) formats.
Style transformation: Excel at converting images to different artistic styles.
OpenAI quality: Powered by advanced vision-language understanding.

Parameters

Parameter	Required	Description
prompt	Yes	Text instruction describing the edit or transformation you want.
image	Yes	Source image to edit (upload or public URL).
quality	No	Output quality: low, medium, or high. Default: medium.
mask_image	No	Optional mask to specify edit regions (upload or URL).
size	No	Output dimensions: 1024x1024, 1024x1536, or 1536x1024.
enable_sync_mode	No	API only: Waits for result and returns it directly.
enable_base64_output	No	API only: Returns base64 string instead of URL.

How to Use

Write your edit instruction — describe the transformation you want (e.g., “Become a comic style”).
Upload your image — drag and drop or paste a public URL.
Choose quality — select low, medium, or high based on your needs.
Add mask (optional) — upload a mask image to limit edits to specific areas.
Select size — choose your desired output dimensions.
Run — click the button to apply the edit.
Download — preview and save your transformed image.

Pricing

Pricing varies by quality level and output size.

Square Output (1024x1024)

Quality	Cost
Low	$0.011
Medium	$0.042
High	$0.167

Rectangular Output (1024x1536 or 1536x1024)

Quality	Cost
Low	$0.016
Medium	$0.063
High	$0.250

Quick Reference

Quality	1024x1024	1024x1536 / 1536x1024
Low	$0.011	$0.016
Medium	$0.042	$0.063
High	$0.167	$0.250

Best Use Cases

Style Transfer — Convert photos to comic, cartoon, painting, or other artistic styles.
Creative Transformation — Reimagine images with different aesthetics or themes.
Regional Editing — Use masks to edit specific areas while preserving the rest.
Content Enhancement — Improve or modify specific aspects of images.
Artistic Interpretation — Transform photos into various art forms.

Example Prompts

“Become a comic style”
“Transform into a watercolor painting”
“Make it look like a vintage photograph from the 1950s”
“Convert to anime style illustration”
“Apply a cyberpunk neon aesthetic”
“Turn into a pencil sketch”

Quality Guide

Quality	Best For	Trade-off
Low	Quick previews, testing concepts, high-volume processing	Fastest, most affordable, lower detail
Medium	General use, social media, balanced needs	Good quality/cost balance
High	Professional work, final deliverables, maximum detail	Highest quality, premium price

Pro Tips for Best Results

Start with medium quality to test your prompt, then upgrade to high for final output.
Use masks when you want to preserve specific areas untouched.
Be specific about the target style — “comic style”, “oil painting”, “anime”.
For style transfers, simpler source images often produce cleaner results.
Rectangular sizes work well for portraits (1024x1536) or landscapes (1536x1024).
The model interprets style instructions creatively — embrace the artistic interpretation.

Notes

If using URLs for images or masks, ensure they are publicly accessible.
The enable_sync_mode and enable_base64_output options are only available through the API.
Mask images should be black and white, where white indicates areas to edit.
Processing time varies by quality level — higher quality takes longer.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/openai/gpt-image-1" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "quality": "medium",
    "size": "auto",
    "enable_sync_mode": false,
    "enable_base64_output": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
prompt	string	Yes		-	The positive prompt for the generation.
image	string	Yes		-	The image to edit.
quality	string	No	medium	high, medium, low	The quality of the generated image.
mask_image	string	No		-	An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. If there are multiple images provided, the mask will be applied on the first image. Must be a valid PNG file
size	string	No	auto	auto, 10241024, 10241536, 1536*1024	The size of the generated media in pixels (width*height).
enable_sync_mode	boolean	No	false	-	If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.
enable_base64_output	boolean	No	false	-	If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Openai Dall E 3 Openai Gpt Image 1 High Fidelity