# Qwen Image 2.0 API

> Qwen Image 2.0 — fast, high-fidelity AI image generation & editing.

- **Provider**: Qwen
- **Model id**: `qwen2-image-edit`
- **Modality**: image
- **Price**: 3.25 credits

## Overview

Qwen Image 2.0 is called in two steps: create a generation task, then poll the task until the result is ready.

## Authentication

All requests require a Bearer Token in the request header:

```
Authorization: Bearer YOUR_API_KEY
```

## Create Task

`POST https://you.bot/api/v1/generate`

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| modelId | string | Yes | Model id: `qwen2-image-edit` |
| input | object | Yes | Input parameters object (see below) |
| callbackUrl | string | No | https URL we POST the finished task to. Signed with `X-Webhook-Signature` once you create a webhook signing key in Dashboard → Settings |

### input object parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| prompt | string | Yes | The prompt to edit the image with Max 5000 characters. (example: Relight this fruit bowl with dramatic side lighting, deepening the shadows and adding a dewy sheen to each grape and plum for a moody Old Master still-life… — full value in the request example) |
| image_url | string[] | Yes | The reference image to guide the edit (image URL) |
| image_size | string | No | Image ratio (options: 1:1 \| 2:3 \| 3:2 \| 3:4 \| 4:3 \| 9:16 \| 16:9 \| 21:9) (default: 16:9) |
| output_format | string | No | Generate image format (options: png \| jpeg) (default: png) |
| seed | number | No | The same seed and the same prompt given to the same version of the model will output the same image every time (default: 0) |
| nsfw_checker | boolean | No | A configurable parameter. Defaults to true in the Playground. (true/false) (default: true) |

### Request example

```json
{
  "modelId": "qwen2-image-edit",
  "input": {
    "prompt": "Relight this fruit bowl with dramatic side lighting, deepening the shadows and adding a dewy sheen to each grape and plum for a moody Old Master still-life look.",
    "image_url": [
      "https://you.bot/examples/grok-imagine-text-to-image.jpg"
    ],
    "image_size": "16:9",
    "output_format": "png",
    "seed": 0,
    "nsfw_checker": true
  }
}
```

### Response example

```json
{
  "taskId": "281e5b0…f39b9",
  "creditsCharged": 3.25
}
```

## Query Task

`GET https://you.bot/api/v1/task/{taskId}?model=qwen2-image-edit`

When `state` is `success`, the output is in `resultUrls`: `{ "state": "success", "resultUrls": [ ... ] }`. (Text models return inline in the create response.)

## Error Codes

| Code | Description |
|------|-------------|
| 200 | Request successful |
| 400 | Invalid request parameters |
| 401 | Authentication failed — check API Key |
| 402 | Insufficient account balance |
| 403 | IP not allowed for this key, or the key is restricted to other models |
| 404 | Task not found, or it has expired |
| 409 | Duplicate request — an identical submit arrived moments ago. Nothing was charged; retry is safe |
| 413 | Payload too large — see the character and file-size limits for this model |
| 429 | Rate limit exceeded — retry after the Retry-After header |
| 500 | Internal server error |
| 504 | Upstream timed out — nothing was delivered; retry is safe |
