GPT Image 1.5 API

Use GPT Image 1.5 on EvoLink as a stable production route for text-to-image, image editing, and async delivery with one API key, pricing visibility, and playground access.

Model Type:

Price: $0.013(~ 0.9 credits) per image

May experience occasional downtime. Suitable for development and testing.

Use the same API endpoint for all versions. Only the model parameter differs.

Prompt

42 (suggested: 2,000)

Input Images

Upload reference images

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 10

Size

Quality

Click Generate to see preview

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

GPT Image 1.5 API Pricing and Production Access

Run GPT Image 1.5 on EvoLink for text-to-image, image editing, and async task delivery. Review pricing, validate prompts in the playground, and move a known image workflow into production with one API.

Pricing

Model	Mode	Price
GPT Image 1.5 Beta	Image Generation	$0.013/ request(0.9 Credits)

GPT Image 1.5 Beta

Image Generation

Price:

$0.013/ request

(0.9 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

What You Can Build with GPT Image 1.5

Production Image Workflows with Fewer Unknowns

GPT Image 1.5 fits teams that want a more established route for image generation and editing instead of chasing the newest label first. It works well when your goal is repeatable output, predictable billing, and a cleaner path from testing to rollout.

Test Production Prompts

Catalog and Marketing Asset Updates

Use GPT Image 1.5 to refresh product listings, campaign creatives, and text-led marketing visuals when teams need a known route with established request behavior and a straightforward async flow.

Try Asset Refresh

Reference-Based Editing for Existing Assets

Send prompts with reference images when you need controlled edits rather than full regeneration. GPT Image 1.5 is useful for teams that already know the workflow they want and need a stable route for repeated editing jobs.

Test Image Editing

Why Use GPT Image 1.5 Through EvoLink

GPT Image 1.5 on EvoLink is best positioned as a known production baseline: one route, visible pricing, playground validation, and an async workflow teams can operationalize without unnecessary uncertainty.

A More Established Production Baseline

GPT Image 1.5 is a better fit when the question is not just image quality, but whether your team wants a route with known request behavior and a more settled rollout story.

Pricing, Playground, and Access on One Page

This page keeps pricing, prompt testing, and request model details together so teams can evaluate production use without stitching information across multiple pages.

Async Delivery That Matches Real Workloads

GPT Image 1.5 uses an async task flow on EvoLink, which is a practical match for real generation and editing jobs that need polling, storage, and workflow handoff.

How to Integrate GPT Image 1.5

Three steps to validate the route, send requests, and retrieve async image results.

Create Your API Key

Sign in to EvoLink and generate one API key for playground testing and production requests. The same access path is used across supported image routes.

Send a GPT Image 1.5 Request

Use the `gpt-image-1.5` model name, then pass your prompt, size, quality, and optional `image_urls` if you need reference-based editing or image-to-image workflows.

Poll the Result and Save the Output

Image generation runs as an async task. Retrieve the completed result, handle workflow completion in your app, and save outputs promptly because generated image links are temporary.

Open Playground

GPT Image 1.5 Capabilities

The practical controls that matter when GPT Image 1.5 is used as a stable production route.

Workflow

Text-to-Image and Image Editing

Use one route for net-new image generation, reference-based editing, and image-to-image style requests.

Editing

Reference Image Support

Attach reference image URLs when your workflow needs controlled changes, repeated edits, or prompt-guided updates from an existing asset.

Controls

Size and Quality Controls

Choose the supported aspect ratios or pixel sizes and adjust quality according to output requirements and expected cost.

Async

Async Task Delivery

Requests return task IDs for polling, which makes it easier to manage production jobs that take longer to complete.

Output

Single-Image Output Path

The route is optimized around one generated result per request, which simplifies downstream approval, storage, and automation handling.

Delivery

Temporary Result URLs

Generated result URLs are time-limited, so production integrations should save completed assets into application storage or an asset pipeline.

Frequently Asked Questions

Everything you need to know about the product and billing.

On EvoLink, GPT Image 1.5 is an image generation route for text-to-image, reference-based editing, and image-to-image workflows. This page is positioned as the production entry point for pricing, playground testing, and API access.

Pricing depends on the route configuration shown on this page. Review the pricing section so your team can evaluate cost against image size, quality, and expected production volume before rollout.

Yes. You can send prompts with optional `image_urls` when you need reference-based edits, controlled variations, or image-to-image style requests rather than net-new generation only.

Use `gpt-image-1.5` as the request model name for this route. Keep that model name consistent across playground validation, implementation, and production deployment.

Yes. GPT Image 1.5 runs through an async task flow on EvoLink. Your app should create the task, poll for completion, and then store or deliver the finished image once the result is ready.

Use the playground on this page to validate prompts, compare settings, and confirm whether GPT Image 1.5 fits your production workflow before integration.

GPT Image 1.5 supports multiple aspect ratios and pixel sizes on EvoLink, along with quality controls you can tune for output needs and budget. Check the request parameters and pricing block on this page for the current options.

Explore the GPT Image family

GPT Image 1.5 remains the clearest production-default route in the GPT Image family for many current teams. Use the family page when your next question is whether to stay on GPT Image 1.5, move to GPT Image 2, or compare against GPT Image 1 as the older baseline.

View GPT Image family Open GPT Image 2 Open GPT Image 1

API Reference

Select endpoint

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/images/generations

Generate Image

Create an image generation task using text prompts or reference images. Supports text-to-image, image-to-image, and image editing modes.

Asynchronous processing mode, use the returned task ID to query status.

Generated image links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: gpt-image-1.5-beta

Image generation model name.

Value	Description
gpt-image-1.5-beta	GPT Image 1.5 Beta model

Examplegpt-image-1.5-beta

promptstringRequired

Prompt describing the image to be generated or how to edit the input image.

Notes

Limited to 2000 tokens

ExampleA beautiful colorful sunset over the ocean

sizestringOptionalDefault: 1:1

Size of generated image.

Value	Description
1:1	Square
2:3	Portrait
3:2	Landscape
1024x1024	Square
1024x1536	Portrait
1536x1024	Landscape

Notes

Aspect ratio format: 1:1, 2:3, 3:2
Pixel format: 1024x1024, 1024x1536, 1536x1024

Example1:1

qualitystringOptionalDefault: auto

Quality of the generated image.

Value	Description
auto	Automatic selection (default)
low	Low quality
medium	Medium quality
high	High quality

Exampleauto

image_urlsarrayOptional

Reference image URL list for image-to-image and image editing features.

Notes

Supports 1-16 images per request
Max size: 50MB per image
Formats: .jpeg, .jpg, .png, .webp
URLs must be directly accessible by the server

Examplehttps://example.com/image1.png

nintegerOptionalDefault: 1

Number of images to generate. Charged per image.

Value	Description
1-10	1 to 10 images per request

Example1

callback_urlstringOptional

HTTPS callback address after task completion.

Notes

Triggered on completion, failure, or cancellation
Sent after billing confirmation
HTTPS only, no internal IPs
Max length: 2048 chars
Timeout: 10s, Max 3 retries

Examplehttps://your-domain.com/webhooks/image-task-completed

Request Example

{
  "model": "gpt-image-1.5-beta",
  "prompt": "A beautiful colorful sunset over the ocean",
  "size": "1:1",
  "quality": "auto",
  "n": 1,
  "callback_url": "https://your-domain.com/webhooks/callback"
}

Response Example

{
  "created": 1757156493,
  "id": "task-unified-1757156493-imcg5zqt",
  "model": "gpt-image-1.5-beta",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 100
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 1.9584,
    "user_group": "default"
  }
}