On this page

Image generationDeveloper Preview

GPT Image 2 API

Generate production-ready images from prompts or reference images through one predictable async API. imya handles model routing, task state, credits, and generated assets.

REST API · v1 · Async tasks

Developer Preview: the public contract is ready for review. Production traffic stays disabled until the /v1 endpoint and billing path pass end-to-end validation.

GPT Image 2 API workflow — One imya API key connects your app to model routing, async task processing, and generated assets.

Make your first request

The API is asynchronous: create a task, keep the returned task ID, then retrieve the task until a result is ready.

1
Create an API key
Generate a key from your imya account settings.
2
Create a task
Send the model ID, prompt, and output options.
3
Retrieve the result
Poll the task or receive a callback when it finishes.

Authentication

Send your imya API key as a Bearer token on every request. Keep it on your server and never expose it in browser code.

HTTP

Authorization: Bearer YOUR_IMYA_API_KEY
Content-Type: application/json

Create an image generation

Creates an asynchronous GPT Image 2 task and reserves the estimated credits.

POST/v1/images/generations

Request

curl https://imya.ai/v1/images/generations \
  -H "Authorization: Bearer YOUR_IMYA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A luxury perfume product photo on warm marble, soft studio light",
    "size": "1:1",
    "quality": "medium",
    "n": 1
  }'

Retrieve a task

Returns the latest task state, final credit usage, generated assets, or a structured error.

GET/v1/tasks/{task_id}

Request

curl https://imya.ai/v1/tasks/task_01jz_example \
  -H "Authorization: Bearer YOUR_IMYA_API_KEY"

Request parameters

Field	Type	Required	Description
model	string	Yes	Use gpt-image-2.
prompt	string	Yes	Text prompt for the image.
size	string	No	1:1, 3:2, 2:3, 4:3, 3:4, 16:9, or 9:16.
quality	string	No	medium or high.
n	number	No	Number of images. Default is 1.
image_urls	string[]	No	Reference images for image-to-image.
callback_url	string	No	Optional HTTPS webhook URL.

Responses

Accepted response

{
  "id": "task_01jz_example",
  "status": "pending",
  "model": "gpt-image-2",
  "credits_reserved": 13
}

Completed response

{
  "id": "task_01jz_example",
  "status": "succeeded",
  "model": "gpt-image-2",
  "credits_used": 13,
  "data": [
    {
      "url": "https://cdn.imya.ai/generated/example.png",
      "width": 1024,
      "height": 1024
    }
  ]
}

Credit billing

Credits belong to the user who owns the API key. The reserved estimate is returned when a task is created; the completed task reports the final amount used. Model, output count, quality, and membership discount determine the final charge.

Task status

pending

The task was accepted and is waiting to start.

processing

The model is generating the requested output.

succeeded

Generation finished and data contains the assets.

failed

Generation failed. Read the structured error object.

Errors

401

Missing or invalid API key.

402

The account does not have enough credits.

422

The model, prompt, size, or quality is invalid.

429

The API key reached its rate or concurrency limit.

500

The generation provider or imya service returned an error.

Want to test the model before integrating?

Open the hosted GPT Image 2 generator to compare prompts and output settings without writing code.

Try GPT Image 2 online

GPT Image 2 API

Generate production-ready images from prompts or reference images through one predictable async API. imya handles model routing, task state, credits, and generated assets.

REST API · v1 · Async tasks

Developer Preview: the public contract is ready for review. Production traffic stays disabled until the /v1 endpoint and billing path pass end-to-end validation.

One imya API key connects your app to model routing, async task processing, and generated assets.

Make your first request

The API is asynchronous: create a task, keep the returned task ID, then retrieve the task until a result is ready.

Create an API key

Generate a key from your imya account settings.

Create a task

Send the model ID, prompt, and output options.

Retrieve the result

Poll the task or receive a callback when it finishes.

curl https://imya.ai/v1/images/generations \ -H "Authorization: Bearer YOUR_IMYA_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-image-2", "prompt": "A luxury perfume product photo on warm marble, soft studio light", "size": "1:1", "quality": "medium", "n": 1 }'

Request parameters

Field	Type	Required	Description
model	string	Yes	Use gpt-image-2.
prompt	string	Yes	Text prompt for the image.
size	string	No	1:1, 3:2, 2:3, 4:3, 3:4, 16:9, or 9:16.
quality	string	No	medium or high.
n	number	No	Number of images. Default is 1.
image_urls	string[]	No	Reference images for image-to-image.
callback_url	string	No	Optional HTTPS webhook URL.

Responses

Accepted response

{
  "id": "task_01jz_example",
  "status": "pending",
  "model": "gpt-image-2",
  "credits_reserved": 13
}

Completed response

{
  "id": "task_01jz_example",
  "status": "succeeded",
  "model": "gpt-image-2",
  "credits_used": 13,
  "data": [
    {
      "url": "https://cdn.imya.ai/generated/example.png",
      "width": 1024,
      "height": 1024
    }
  ]
}