GPT Image 1

Overview

GPT Image 1 is an OpenAI image generation model for prompt-based image creation and reference-guided generation. Use this page when you are ready to call the API after trying the model in the APIXO playground.

Capability	Value
Model ID	`gpt-image-1`
Mode	`gpt-image-1`
Prompt length	1-10000 characters
Reference images	0-5 URLs
Aspect ratios	`1:1`, `2:3`, `3:2`
Number of images	`1`, `2`, `4`

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/gpt-image-1`	Submit a generation task
`GET`	`/statusTask/gpt-image-1?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request submits a text-to-image task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/gpt-image-1" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "gpt-image-1",
      "prompt": "a cozy cyberpunk cafe with neon lights",
      "aspect_ratio": "3:2",
      "num_images": 1
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/gpt-image-1?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://r2.apixo.ai/xxx.png\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "SensitiveContent",
    "failMsg": "Content violates provider policy, please adjust the prompt",
    "createTime": 1767965610929,
    "completeTime": 1767965620132,
    "costTime": 9040
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const imageUrls = payload.resultUrls;

Request body

Text-to-image

{
  "request_type": "async",
  "input": {
    "mode": "gpt-image-1",
    "prompt": "a cozy cyberpunk cafe with neon lights",
    "aspect_ratio": "3:2",
    "num_images": 1
  }
}

Reference-guided generation

{
  "request_type": "async",
  "input": {
    "mode": "gpt-image-1",
    "prompt": "turn these references into a futuristic cityscape at sunset",
    "image_urls": [
      "https://example.com/ref1.jpg",
      "https://example.com/ref2.png"
    ],
    "aspect_ratio": "3:2",
    "num_images": 2
  }
}

Parameters

request_type

string

default:"async"

required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

callback_url

string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

input

object

required

GPT Image 1 input parameters.

Show properties

mode

string

required

APIXO routing mode. Supported value: gpt-image-1.

prompt

string

required

Text prompt describing the desired image. Supports 1-10000 characters.

aspect_ratio

string

required

Output aspect ratio. Supported values: 1:1, 2:3, 3:2.

num_images

integer

required

Number of images to generate. Supported values: 1, 2, 4. Legacy requests may use nVariants, but new integrations should use num_images.

image_urls

string[]

Optional reference image URLs. Supports up to 5 public HTTP(S) image URLs.

Response format

Submit task response

POST /generateTask/gpt-image-1 returns a task ID when the task is accepted:

code

integer

API status code. 200 means the task was accepted.

message

string

Human-readable status message.

data.taskId

string

Unique task identifier used with the status endpoint.

Status response fields

taskId

string

Unique task identifier.

state

string

Current task state: processing, success, or failed.

resultJson

string

JSON string containing the generated image URLs. Present when state is success.

failCode

string

Machine-readable failure code. Present when state is failed.

failMsg

string

Human-readable failure message. Present when state is failed.

createTime

integer

Task creation timestamp in Unix milliseconds.

completeTime

integer

Task completion timestamp in Unix milliseconds. Present after completion.

costTime

integer

Processing duration in milliseconds. Present after completion.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/gpt-image-1" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "gpt-image-1",
      "prompt": "a clean product photo of wireless earbuds on soft stone",
      "aspect_ratio": "1:1",
      "num_images": 1
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

GPT Image 1 is billed per generated image. The selected num_images value determines the number of images requested.

Unit	APIXO price	Market price
Image	`$0.35 / image`	`$0.40 / image`

For current route and market comparison pricing, see Pricing.

Latency and polling

Actual latency may vary by prompt complexity, reference image count, provider route, and current queue load.

Typical generation time	Recommended first poll	Poll interval
About 30 seconds	20 seconds after task creation	3-10 seconds

For high-concurrency production workloads, use callback mode to avoid frequent polling.

Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, mode, parameter, prompt, or image URL shape	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`429`	Rate limit, daily quota, or provider rate limit reached	Retry with exponential backoff
`500`	Server error or unknown upstream error	Retry with backoff
`502`	Upstream provider error	Retry with backoff
`504`	Upstream timeout	Retry or use callback mode for long-running jobs

Task failure codes

Fail code	Meaning	What to do
`SensitiveContent`	Prompt or output was rejected by provider safety checks	Change the prompt or reference image
`PromptInvalid`	Prompt format or content was rejected	Revise the prompt
`ImageNotAccess`	A reference image URL could not be reached	Use a public, direct image URL
`ImageFormatIncorrect`	Image format is incorrect	Use a supported image format
`RateLimited`	Provider or account rate limit was reached	Retry with backoff
`Timeout`	Generation did not finish in time	Retry, reduce input complexity, or use callback mode
`Unknown error`	Unmapped provider-side failure	Retry with backoff or try another route

Tips

prompt must be a non-empty string and cannot exceed 10000 characters.
aspect_ratio is required. Use 1:1 for square outputs, 3:2 for landscape images, or 2:3 for portrait images.
num_images is required. Supported values are 1, 2, and 4.
image_urls supports JPG, PNG, and WebP reference images, up to 10 MB per image. Use public, direct HTTP(S) image URLs.
Result URLs are normally stored for 15 days. Download and store important outputs promptly.

See Error Codes for the full error reference.

Getting Started

Image Models

Video Models

Audio Models

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-image

Reference-guided generation

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Tips

Getting Started

Image Models

Video Models

Audio Models

Documentation Index

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-image

​Reference-guided generation

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Task failure codes

​Tips

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-image

Reference-guided generation

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Task failure codes

Tips

Related links