Model guide

Qwen Image API: versions, prices and code

Alibaba's Qwen Image models are a low-cost choice for pictures with text in many languages and for edits by instruction. This guide covers the seven versions on Revana, what each costs and how to call them.

Every Qwen Image model in the catalogue

Qwen Image is Alibaba's image family. It is known for rendering text inside pictures, in Chinese as well as English, and for following edit instructions closely. Revana carries seven versions, all on the same request format:

Qwen Image models compared
ModelModel idDoesSizesReference imagesPrice fromRoutes
Qwen Image 3.0qwen-image-3.0text to image, editing1K, 2Kup to 3$0.03two routes
Qwen Image 3.0 Proqwen-image-3.0-protext to image, editing1K, 2Kup to 3$0.04two routes
Qwen Image 2.1qwen-image-2.1text to image, editing1K, 2Kone image$0.03one route
Qwen Image 2.0qwen-image-2.0text to image, editing1K, 2Kone image$0.03two routes
Qwen Image 2.0 Proqwen-image-2.0-protext to image, editing1K, 2Kone image$0.07one route
Qwen Imageqwen-imagetext to image, editingmodel defaultone image$0.03one route
Qwen Image Editqwen-image-editediting onlymodel defaultone image$0.04one route

Prices are per image. For a new project, start with Qwen Image 3.0: it is the newest standard tier, it takes up to three reference images, and it costs $0.03 at 2K as well as 1K. Move to 3.0 Pro if the standard tier misses details you need, and keep the older versions for prompts you have already tuned.

Qwen Image pricing (October 2026)

Qwen Image price per image and per batch
ModelSizePer image100 images1,000 images
Qwen Image 3.01K or 2K$0.03$3.00$30.00
Qwen Image 3.0 Pro1K$0.04$4.00$40.00
Qwen Image 3.0 Pro2K$0.08$8.00$80.00
Qwen Image 2.11K$0.03$3.00$30.00
Qwen Image 2.12K$0.05$5.00$50.00
Qwen Image 2.01K or 2K$0.03$3.00$30.00
Qwen Image 2.0 Pro1K or 2K$0.07$7.00$70.00
Qwen Imageone size$0.03$3.00$30.00
Qwen Image Editone size$0.04$4.00$40.00

Two pricing details are easy to miss. Qwen Image 3.0 charges the same at 1K and 2K, so there is no reason to ask for the smaller size. Qwen Image 3.0 Pro doubles from 1K to 2K, so draft at 1K and render the keepers at 2K. Failed images are never charged.

What Qwen Image is good for

  • Text in languages other than English. Shop signs, menus, labels and posters in Chinese, or Chinese and English in one picture.
  • Instruction edits. "Change the jacket to red", "remove the person on the left", "replace the sign text with OPEN". Qwen Image Edit does only this; the newer versions do it as well as text to image.
  • Low cost per image. At $0.03 per image, Qwen Image 3.0 is one of the cheaper ways to make large batches of marketing variants.

We do not publish quality scores. For text-heavy English layouts, compare against GPT Image 2 and Nano Banana Pro with your own prompts before you commit.

Generate a Qwen Image 3.0 picture

Send POST /v1/generations with the model id and an input, then poll the generation. This 2K image costs $0.03.

cURL
export REVANA_API_KEY="sr_live_..."

# 1. Submit the job (returns 202 with the generation id)
curl https://api.revana.si/v1/generations \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-3.0",
    "input": {
      "prompt": "A night street in Shanghai, a small noodle shop with a red paper lantern. The wooden sign above the door reads 老街面馆 in brush calligraphy. Light rain, reflections on the pavement.",
      "resolution": "2K"
    },
    "max_cost_usd": 0.1
  }'

# 2. Poll with the id from step 1 until status is "succeeded" or "failed"
curl https://api.revana.si/v1/generations/gen_01JC2V8K5T \
  -H "Authorization: Bearer $REVANA_API_KEY"
Python
import os
import time

import requests

API = "https://api.revana.si/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['REVANA_API_KEY']}"}

resp = requests.post(f"{API}/generations", headers=HEADERS, json={
    "model": "qwen-image-3.0",
    "input": {
        "prompt": "A night street in Shanghai, a small noodle shop with a red paper lantern. The wooden sign above the door reads 老街面馆 in brush calligraphy. Light rain, reflections on the pavement.",
        "resolution": "2K",
    },
    "max_cost_usd": 0.1,
})
resp.raise_for_status()
job = resp.json()

while job["status"] in ("queued", "running"):
    time.sleep(3)
    job = requests.get(f"{API}/generations/{job['id']}", headers=HEADERS).json()

if job["status"] == "succeeded":
    print(job["output"]["urls"], job["cost_usd"])
else:
    print("Failed:", job["error"])
Node.js
// Node 18 or later. Save as generate.mjs and run: node generate.mjs
const API = "https://api.revana.si/v1";
const headers = {
  Authorization: `Bearer ${process.env.REVANA_API_KEY}`,
  "Content-Type": "application/json",
};

const res = await fetch(`${API}/generations`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    model: "qwen-image-3.0",
    input: {
      prompt: "A night street in Shanghai, a small noodle shop with a red paper lantern. The wooden sign above the door reads 老街面馆 in brush calligraphy. Light rain, reflections on the pavement.",
      resolution: "2K",
    },
    max_cost_usd: 0.1,
  }),
});
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
let job = await res.json();

while (job.status === "queued" || job.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  job = await (await fetch(`${API}/generations/${job.id}`, { headers })).json();
}

if (job.status === "succeeded") console.log(job.output.urls, job.cost_usd);
else console.error("Failed:", job.error);
Response
{
  "id": "gen_01JC2V8K5T",
  "model": "qwen-image-3.0",
  "status": "succeeded",
  "output": {
    "urls": [
      "https://cdn.revana.si/g/gen_01JC2V8K5T/0.png"
    ]
  },
  "cost_usd": 0.03,
  "attempts": 1,
  "error": null,
  "created_at": "2026-10-28T10:14:02Z",
  "completed_at": "2026-10-28T10:15:31Z"
}

Edit an image with an instruction

For an edit, send the picture and say what to change. Qwen Image 3.0 and 3.0 Pro accept up to three pictures in image_urls; the other versions take one, in image_url. This edit on Qwen Image Edit costs $0.04:

Request body
{
  "model": "qwen-image-edit",
  "input": {
    "prompt": "Replace the text on the shop sign with FRESH BREAD DAILY, in the same font and colour. Change nothing else.",
    "image_url": "https://example.com/bakery-front.jpg"
  },
  "max_cost_usd": 0.1
}

Sending more pictures than a model takes is refused straight away with 422 invalid_input, and the message says the limit. Nothing is charged for a refused request.

All Qwen versions are on the models page, with the request reference in the docs and credit packs on the pricing page. Get an API key to run the samples.

Frequently asked questions

How much does the Qwen Image API cost?

In October 2026, Qwen Image 3.0 costs $0.03 per image at 1K or 2K, Qwen Image 3.0 Pro costs $0.04 at 1K and $0.08 at 2K, and Qwen Image Edit costs $0.04 per edit.

Which Qwen Image version should I use?

Start with Qwen Image 3.0. It is the newest standard tier, takes up to three reference images and costs the same at 1K and 2K. Try 3.0 Pro when you need more detail.

Can Qwen Image render Chinese text?

Yes. Rendering text in Chinese as well as English is what the Qwen Image family is known for. Put the exact characters in the prompt, and check the result before you publish it.

What is the difference between Qwen Image and Qwen Image Edit?

Qwen Image Edit only edits a picture you send. The other Qwen Image versions make pictures from a prompt and also edit.

How many images can I send to Qwen Image 3.0?

Up to three, in image_urls. Older versions take one picture, in image_url.

Try Qwen Image with one key

One API key for every Qwen Image version and every other image and video model. Prepaid credit from $10, charged only for images that are delivered.