Qwen Image Edit
Qwen Image Edit is Alibaba's text-driven image editing model, give it a source image and a natural-language edit instruction and it returns the modified result in a single pass. Handles object addition/removal, style transfer, background replacement, and attribute edits (clothing, expression, age). Pairs well with FLUX.1 Kontext Pro for premium edits, and is the cheap-tier default for production batch editing workloads.
Pricing
Input
$0.020 / image
Output
—
Pay only for what you use. No subscriptions, no monthly minimum.
Specs
- Context
- —
- Max output
- —
- Latency
- Medium
- Category
- Image
- Arabic
- Partial
Constraints & limits
Output
Presigned URLs (~24h TTL)
The gateway auto-clamps requests to the model's limits where possible.
Quick start
This sample hits the image generation endpoint. Change base_url and your key, then run it.
from openai import OpenAI
client = OpenAI(
api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
base_url="https://api.thalam.ai/v1",
)
response = client.images.generate(
model="qwen/qwen-image-edit",
prompt="A futuristic city skyline at sunset.",
size="1024x1024",
n=1,
)
print(response.data[0].url)Similar models
GPT Image 2.5 Fast
The quick half of GPT Image 2.5. Five detail levels, from a cent-scale draft to a finished frame, billed on what it actually renders.
GPT Image 2.5 Precise
The editing half of GPT Image 2.5. Give it up to four images and a prompt, and it changes what you asked for and leaves the rest alone.