openai/gpt-image-1.5/edit
Gpt Image 1.5 Edit by OpenAI - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runopenai/gpt-image-1.5/editInput Schema
8 parameters · 1 required · 7 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | The prompt for image generation · Min length: 2 · Max length: 32000 |
mask | string | Optional | The URL of the mask image to use for the generation. This indicates what part of the image to edit. |
images | string[] | Optional | The URLs of the images to use as a reference for the generation. |
quality | string | Optional | Quality for the generated image · Options: low, medium, high · Default: "high" lowmediumhigh |
background | string | Optional | Background for the generated image · Options: auto, transparent, opaque · Default: "auto" autotransparentopaque |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 1:1, 2:3, 3:2 1:12:33:2 |
output_format | string | Optional | Output format for the images · Options: jpeg, png · Default: "png" jpegpng |
input_fidelity | string | Optional | Input fidelity for the generated image · Options: low, high · Default: "high" lowhigh |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "openai/gpt-image-1.5/edit",
"images": [
"https://static.sandbase.ai/examples/openai/gpt-image-1.5/edit/input_images_0.png"
],
"prompt": "Same workers, same beam, same lunch boxes - but they're all on their phones now. One is taking a selfie. One is on a call looking annoyed. Same danger, new priorities. A hard hat has AirPods.",
"quality": "high",
"background": "auto",
"output_format": "png",
"input_fidelity": "high"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
GPT Image 1.5 Edit
GPT Image 1.5 Edit applies natural-language changes to one or more source images while preserving the visual information that should remain stable. It is designed for iterative creative work such as product changes, compositing, localized replacement, background treatment, and campaign variation where rebuilding the entire image would lose important identity or layout cues.
The model combines strong instruction following with improved rendering of text and dense compositions. It can reconcile several references, maintain recognizable people or products, and make targeted changes through written direction or a mask, supporting both precise corrections and broader art-directed revisions.
Highlights
Precise instruction following. Applies detailed edit requests while distinguishing requested changes from content that should remain intact.
High-fidelity preservation. Maintains recognizable people, products, style, and composition across iterative revisions.
Multi-image composition. Combines information from several references into a coherent edited result.
Improved text rendering. Creates and revises typography more reliably inside posters, interfaces, packaging, and designed scenes.
Pricing
| Quality | 1:1 | 2:3 or 3:2 |
|---|---|---|
| Low | $0.009 | $0.013 |
| Medium | $0.034 | $0.051 |
| High | $0.133 | $0.200 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The model's named workflow matches the source material and intended output | A different input modality or model route is required |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{
"aspect_ratio": "1:1",
"images": [
"https://static.sandbase.ai/examples/openai/gpt-image-1.5/edit/input_images_0.png"
],
"output_format": "png",
"prompt": "Same workers, same beam, same lunch boxes - but they're all on their phones now. One is taking a selfie. One is on a call looking annoyed. Same danger, new priorities. A hard hat has AirPods."
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | openai/gpt-image-1.5/edit |
| Inputs | aspect_ratio, background, images, input_fidelity, mask, output_format, prompt, quality |
| Required inputs | prompt |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |
| Aspect Ratio | 1:1 / 2:3 / 3:2 |
| Output Format | jpeg / png |
| Quality | low / medium / high |
Related Models
openai/gpt-image-1.5— Compare a nearby route in the same local model family.openai/gpt-image-1— Compare a nearby route in the same local model family.openai/gpt-image-1-mini— Compare a nearby route in the same local model family.