GPT Image 1 API

Use GPT Image 1 on EvoLink for text-to-image, image-to-image, and image editing workflows with flexible quality settings, reference image support, and async task handling.

Model Type:

Est.Price: $0.0098 - 0.446(~ 0.66586 - 30.31603 credits) per image

Highest stability with guaranteed 99.9% uptime. Recommended for production environments.

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

Prompt

0 (suggested: 2,000)

Input Images

Upload up to 16 images (max 50MB each)

Click to upload or drag and drop

Supported formats: JPEG, JPG, PNG, WEBP
Maximum file size: 50MB; Maximum files: 16

Size

Quality

Count

Number of images to generate (1-10)

Click Generate to see preview

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

GPT Image 1 API Pricing and Editing Access

Run GPT Image 1 on EvoLink for text-to-image, image-to-image, and image editing workflows. Review pricing, quality controls, and async task delivery when you need a flexible route for existing image pipelines.

Billing Model

•Token-based — charged by the token counts reported in the upstream usage object.
•Image Output tokens scale with size and quality (low/medium/high).
•Image Input tokens apply only in image-to-image / edit mode.
•Cached Input is charged only when the upstream usage object reports cached tokens.
•Output Text + Thinking (model reasoning + refined prompt) is returned alongside the image at no extra charge by OpenAI. gpt-image-1.5 bills this dimension separately.

Pricing

Model	Mode	Token Category	Price
GPT Image 1	Token-based billing	Image Output	$0.036/ 1K tokens(2.448 Credits)
GPT Image 1	Token-based billing	Image Input	$0.0090/ 1K tokens(0.612 Credits)
GPT Image 1	Token-based billing	Image Cached Input	$0.0022/ 1K tokens(0.153 Credits)
GPT Image 1	Token-based billing	Text Input	$0.0045/ 1K tokens(0.306 Credits)
GPT Image 1	Token-based billing	Text Cached Input	$0.0011/ 1K tokens(0.0765 Credits)

GPT Image 1

Token-based billing

Token Category:Image Output

Price:

$0.036/ 1K tokens

(2.448 Credits)

GPT Image 1

Token-based billing

Token Category:Image Input

Price:

$0.0090/ 1K tokens

(0.612 Credits)

GPT Image 1

Token-based billing

Token Category:Image Cached Input

Price:

$0.0022/ 1K tokens

(0.153 Credits)

GPT Image 1

Token-based billing

Token Category:Text Input

Price:

$0.0045/ 1K tokens

(0.306 Credits)

GPT Image 1

Token-based billing

Token Category:Text Cached Input

Price:

$0.0011/ 1K tokens

(0.0765 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

Editing-Heavy Image Workflows

GPT Image 1 is a useful route when your workflow depends on image-to-image changes, reference-guided edits, and quality tuning instead of only chasing the newest model label. It fits teams that want flexible controls and a known editing surface.

Try Editing Workflows

Reference-Based Asset Variations

Send one or more reference images when you need variant generation, style shifts, or compositional updates from an existing source. GPT Image 1 is especially useful when reference handling matters more than purely net-new output.

Test Reference Images

Legacy-Compatible Production Integrations

GPT Image 1 also works as a compatibility route for teams already familiar with its request model, pricing multipliers, and editing behavior. That makes it a practical option when migration speed matters less than predictability.

Review Model Access

Why Use GPT Image 1 Through EvoLink

GPT Image 1 on EvoLink is best framed as a flexible editing and compatibility route: clear pricing logic, multiple request controls, reference image support, and async task handling for teams that still need this model.

A Flexible Route for Editing and Variations

GPT Image 1 is still useful when your main requirement is image editing, image-to-image behavior, and request-level control over quality, size, and reference handling.

Transparent Pricing Multipliers

This route gives teams explicit control over quality, size, and count, making it easier to reason about cost before sending larger or more frequent image jobs.

Async Delivery for Longer Jobs

Requests run through an async task flow, which is a better fit for generation, editing, and batch-style workloads than assuming immediate sync responses.

How to Integrate GPT Image 1

Three steps to send requests, manage task polling, and work with editing-oriented parameters.

Create Your API Key

Sign in to EvoLink and create one API key for playground testing and production requests. You can use the same access path across supported image routes.

Build the Request Payload

Use `gpt-image-1` as the model name, then pass your prompt, quality, size, and optional reference images. This route is especially useful when you need more explicit control over editing-style requests.

Poll the Task and Save the Result

GPT Image 1 runs through an async task flow. Retrieve the task result when ready, then save the completed image promptly because output URLs are temporary.

Open Playground

GPT Image 1 Capabilities

The request controls and editing behavior that still matter for teams using GPT Image 1.

Pricing

Quality Multipliers

Choose low, medium, or high quality settings depending on the speed, cost, and output fidelity your workflow requires.

Controls

Multiple Size Options

Use supported aspect ratios and pixel dimensions to fit different delivery needs without rewriting the route.

Batch

Batch Generation Support

Generate multiple outputs in one request when you need iterative variants or bulk image jobs from the same prompt setup.

Editing

Reference Image Inputs

Attach up to multiple reference images for image-to-image and editing tasks when your workflow depends on existing source assets.

Async

Async Task Processing

Use task polling to manage longer-running jobs and retrieve results cleanly inside application workflows.

Usage

Commercial Usage Rights

Outputs generated through GPT Image 1 on EvoLink are positioned for commercial use cases, making the route suitable for product and business workflows.

Frequently Asked Questions

Everything you need to know about the product and billing.

On EvoLink, GPT Image 1 is an image generation route for text-to-image, image-to-image, and image editing workflows. It is best treated as a flexible model access page for teams that still need this request surface.

Pricing follows the route settings shown on this page, including quality, size, and output count. That structure makes GPT Image 1 useful when teams want explicit cost control over editing and batch-style jobs.

Yes. GPT Image 1 supports image-to-image requests and reference-based editing flows, including the use of optional reference images for controlled transformations.

Use `gpt-image-1` as the request model name for this route. Keep that model name consistent across testing, implementation, and production handling.

GPT Image 1 supports multiple reference images per request, which is useful for editing tasks, composite-style changes, and workflows built around existing source assets.

Yes. GPT Image 1 supports batch-style generation, which makes it useful for iterative variants and repeated output jobs when your workflow needs more than one image from the same request setup.

When you submit a request, EvoLink returns a task ID. Poll the task endpoint to check progress, retrieve the finished result, and then save the output because generated image URLs are temporary.

Use the API section on this page to review request structure, parameter handling, and async task behavior before shipping GPT Image 1 into production.

Explore the GPT Image family

GPT Image 1 is the older baseline in the GPT Image family on EvoLink. Use the family page when you need to compare this legacy route against GPT Image 1.5 or GPT Image 2 before choosing the best current fit.

View GPT Image family Open GPT Image 2 Open GPT Image 1.5

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

GPT Image 1 (gpt-image-1) model 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

Image generation model name.

Value	Description
gpt-image-1	GPT Image 1 model

Examplegpt-image-1

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: 1024x1024

Size of generated image, supports two formats.

Value	Description
1:1	Square aspect ratio
2:3	Portrait aspect ratio
3:2	Landscape aspect ratio
1024x1024	Square (default)
1024x1536	Portrait
1536x1024	Landscape

Notes

Aspect ratio format: 1:1, 2:3, 3:2
Pixel format: 1024x1024, 1024x1536, 1536x1024
Larger sizes produce more output tokens and higher cost

Example1024x1024

qualitystringOptionalDefault: high

Quality of the generated image. Affects pricing.

Value	Description
low	Low quality, faster — fewest output tokens
medium	Medium quality — balanced
high	High quality, slower (default) — most output tokens

Examplehigh

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.

Value	Description
1-10	Range from 1 to 10 images

Notes

Each image is billed independently by token usage

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

Pricing Information

Billing Model: Token-based — charged by the token counts reported in the upstream usage object.

Token Categories:

Image Output — scales with size and quality (low/medium/high)
Image Input — applies only in image-to-image / edit mode
Image Cached Input — charged when cached tokens are reported
Text Input — prompt token consumption
Text Cached Input — charged when cached prompt tokens are reported

See the Pricing tab for per-token rates by user group.

Request Example

{
  "model": "gpt-image-1",
  "prompt": "A beautiful colorful sunset over the ocean",
  "size": "1024x1024",
  "quality": "medium",
  "n": 1,
  "callback_url": "https://your-domain.com/webhooks/callback"
}

Response Example

{
  "created": 1757156493,
  "id": "task-unified-1757156493-imcg5zqt",
  "model": "gpt-image-1",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 100
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_token",
    "credits_reserved": 2.45,
    "user_group": "default"
  }
}