qwen-image-2

Quick example

curl https://reapi.ai/api/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-2",
    "prompt": "a vintage travel poster that reads VISIT MARS in bold retro type",
    "image_size": "16:9"
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/images/generations",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "qwen-image-2",
        "prompt": "a vintage travel poster that reads VISIT MARS in bold retro type",
        "image_size": "16:9",
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen-image-2",
    prompt: "a vintage travel poster that reads VISIT MARS in bold retro type",
    image_size: "16:9",
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":      "qwen-image-2",
        "prompt":     "a vintage travel poster that reads VISIT MARS in bold retro type",
        "image_size": "16:9",
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/images/generations", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Submit response

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "qwen-image-2",
  "status": "processing",
  "created_at": 1735000000
}

Poll GET /api/v1/tasks/{id} (see the Tasks reference) until status === "completed". The completed payload's output.image_urls holds the generated image URL.

Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Endpoint

POST /api/v1/images/generations
GET  /api/v1/tasks/{id}

Submission is async. The POST returns immediately with a task_id; the task endpoint returns the same envelope until completion. Polling does not consume credits.

Modes

There is no mode field — the modality is implicit in the request shape:

• Text-to-image — no image_url. prompt is required.
• Image editing — pass a single image_url. prompt describes the change (background swap, object edit, restyle, in-frame text rewrite).

Each request produces exactly one image — there is no n parameter.

Request body

model — string, required

Must be qwen-image-2.

prompt — string, required

Up to 800 characters. Required for both text-to-image and editing.

image_url — string, optional

A single source image for editing. Public HTTPS URL only — base64 / data: URIs are rejected at the gateway. Passing it switches the request to editing mode; omit it for text-to-image.

image_size — string, optional, default 16:9

Output aspect ratio.

• Text-to-image accepts: 1:1, 3:4, 4:3, 9:16, 16:9.
• Editing additionally accepts: 2:3, 3:2, 21:9.

output_format — string, optional, default png

One of png or jpeg.

seed — integer, optional

The same seed with the same prompt yields a repeatable result.

nsfw_checker — boolean, optional, default false

Enables upstream content moderation. Off by default.

Pricing

Qwen Image 2 bills a flat rate per generated image, independent of modality, resolution, and aspect ratio. Each request produces one image:

credits = ceil(per_image_usd × 1000)

where 1 credit = $0.001 USD. Failed and rejected requests are not charged.

The exact per-image credit cost surfaces on the model page and through the playground estimator before submit.

Response

The poll envelope returns the image URL in output.image_urls:

{
  "id": "task_019dfd44b7fd74168541552a3260a623",
  "model": "qwen-image-2",
  "status": "completed",
  "output": {
    "image_urls": [
      "https://cdn.reapi.ai/...png"
    ]
  }
}

Generated URLs expire — mirror them to your own storage if you need long-term retention.

Errors

Failures return the standard reAPI envelope { error: { code, message, request_id } }. Common cases:

• Invalid input (prompt over 800 characters, an editing-only image_size in text-to-image, a non-HTTPS image_url) → 400.
• Insufficient credits → 402.
• Rate limited → 429.

See the full catalog at /docs/api/errors.

Tips

• The modality is decided by your inputs, not a flag — omit image_url for generation, include it to edit.
• Put the literal text you want rendered in the prompt — Qwen Image 2 is tuned for legible in-image typography, so spelling out headline copy works.
• For wide layouts, 21:9 is available only when editing (pass an image_url).
• To produce a set of images, send multiple requests — each is billed as one image.

Related

• Image generation models
• Wan 2.7 Image
• Tasks API
• Error codes