Qwen Image 3.0 API

Overview

Qwen Image 3.0 is an asynchronous image generation and editing API. Use text-to-image for prompt-only generation, or image-to-image when you want to guide the output with one to three reference images.

Capability	Value
Model ID	`qwen-image-3-0`
Modes	`text-to-image`, `image-to-image`
Output count	One generated image per accepted task
Prompt	Required, non-empty string
Image-to-image prompt limit	Maximum `800` characters
Reference images	Required for `image-to-image`; `1-3` public image URLs
Aspect ratios	`1:1`, `1:2`, `2:1`, `1:3`, `3:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `9:21`, `21:9`
Default aspect ratio	`1:1` for `text-to-image`; omitted `image-to-image` ratio follows the first input image
Resolution tiers	`1k`, `2k`
Prompt expansion	`enable_prompt_expansion`, default `true`
Seed	`-1` for random, or `0-2147483647`

Endpoint and authentication

Base URL:

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

Method	Endpoint	Purpose
`POST`	`/generateTask/qwen-image-3-0`	Submit an image generation or editing task
`GET`	`/statusTask/qwen-image-3-0?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

curl -X POST "https://api.apixo.ai/api/v1/generateTask/qwen-image-3-0" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-image",
      "prompt": "a clean editorial poster for a bookstore opening, crisp readable typography, warm daylight",
      "aspect_ratio": "4:3",
      "resolution": "1k",
      "enable_prompt_expansion": true,
      "seed": -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/qwen-image-3-0?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://file.apixo.ai/image.png\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "InvalidParameter",
    "failMsg": "The parameter is invalid",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

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": "text-to-image",
    "prompt": "a minimalist product poster for wireless earbuds, clean layout, sharp text",
    "aspect_ratio": "16:9",
    "resolution": "1k",
    "enable_prompt_expansion": true,
    "seed": -1
  }
}

Image-to-image

{
  "request_type": "callback",
  "callback_url": "https://your-server.com/webhooks/apixo",
  "input": {
    "mode": "image-to-image",
    "prompt": "turn this product photo into a polished e-commerce hero image with soft studio lighting",
    "image_urls": [
      "https://example.com/product.png"
    ],
    "resolution": "2k",
    "enable_prompt_expansion": true,
    "seed": 123456
  }
}

In image-to-image mode, omit aspect_ratio when you want the output to follow the first input image ratio. If you provide aspect_ratio, it must be one of the supported ratios below.

Parameters

string

default:"async"

required

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

string

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

object

required

Qwen Image 3.0 input parameters.

Show properties

string

required

Generation mode. Supported values: text-to-image, image-to-image.

string

required

Text prompt describing the desired image or edit. Leading and trailing whitespace is ignored for validation. For image-to-image, the prompt cannot exceed 800 characters.

string[]

Reference image URLs. Required for image-to-image; provide 1-3 public, directly fetchable image URLs. Ignored for text-to-image.

string

default:"1:1"

Output aspect ratio. Supported values: 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9. For text-to-image, blank or omitted values default to 1:1; for image-to-image, blank or omitted values follow the first input image ratio.

string

default:"1k"

Output resolution tier. Supported values: 1k, 2k. The API accepts either lowercase or uppercase values and normalizes them for billing and processing.

boolean

default:"true"

Whether to enable prompt expansion before generation. Supported values: true, false.

integer

default:"-1"

Random seed. Use -1 for random output, or send an integer from 0 through 2147483647 for more repeatable experiments.

Response format

Submit task response

POST /generateTask/qwen-image-3-0 returns a task ID when the task is accepted:

integer

API status code. 200 means the task was accepted.

string

Human-readable status message.

string

Unique task identifier used with the status endpoint.

Status response fields

string

Unique task identifier.

string

Current task state: pending, processing, success, or failed.

string

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

string

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

string

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

integer

Task creation timestamp in Unix milliseconds.

integer

Task completion timestamp in Unix milliseconds. Present after completion.

integer

Processing duration in milliseconds when available.

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/qwen-image-3-0" \
  -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": "image-to-image",
      "prompt": "keep the product identity, improve the lighting, and replace the background with a clean studio set",
      "image_urls": [
        "https://example.com/product.png"
      ],
      "resolution": "2k"
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Qwen Image 3.0 is billed per generated image. Each accepted task produces one image, and image-to-image pricing also depends on the number of input image URLs.

Mode	Resolution	Input images	APIXO price
`text-to-image`	`1k`	`0`	`$0.030 / image`
`text-to-image`	`2k`	`0`	`$0.030 / image`
`image-to-image`	`1k`	`1`	`$0.033 / image`
`image-to-image`	`1k`	`2`	`$0.036 / image`
`image-to-image`	`1k`	`3`	`$0.039 / image`
`image-to-image`	`2k`	`1`	`$0.033 / image`
`image-to-image`	`2k`	`2`	`$0.036 / image`
`image-to-image`	`2k`	`3`	`$0.039 / image`

Billing behavior:

precharge = unit_price_for_mode_resolution_and_input_image_count
final_charge = unit_price when the generated image succeeds
refund = precharge - final_charge

For current discounts and market comparison pricing, see Pricing.

Latency and polling

Qwen Image 3.0 tasks are asynchronous. Actual latency varies by prompt complexity, reference image accessibility, selected resolution, and current queue load.

Workflow	Recommended first poll	Poll interval
Text-to-image	10s after task creation	5s-10s
Image-to-image	10s-15s after task creation	5s-10s

For production queues or batches, use callback mode to avoid frequent polling.

Rate limits and concurrency can vary by account, API key, and model. 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, parameter type, or value	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 account cannot access the model	Check permissions and account status
`404`	Task not found	Verify the `taskId` and model ID
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server or unmapped model error	Retry with backoff
`502`	Model service error	Retry with backoff
`504`	Model service timeout	Retry or use callback mode for long-running jobs

Request validation

Condition	Backend behavior
Missing `input`	Returns a missing-parameter error
Missing or invalid `mode`	Returns `Invalid mode type. Supported: text-to-image, image-to-image`
Missing, non-string, or empty `prompt`	Returns a prompt validation error
`image-to-image` prompt exceeds `800` characters	Returns a prompt length error
Missing `image_urls` for `image-to-image`	Returns a missing-parameter error
`image_urls` is not an array, contains empty values, or contains more than `3` items	Returns an image URL validation error
Invalid `aspect_ratio`	Returns the supported aspect-ratio list
Invalid `resolution`	Returns `The parameter {{resolution}} is invalid. Supported: 1k, 2k.`
Invalid `enable_prompt_expansion`	Returns a boolean type error
Invalid `seed`	Returns the supported seed range

See Error Codes for the full error reference.

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-image

​Image-to-image

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Request validation

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-image

Image-to-image

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Request validation

Related links