Generate and edit images with Qwen-Image.
Qwen-Image-3.0-Pro
New Launched on IteraCompute
qwen/qwen-image-3.0-pro- Tool calling
UnsupportedTool calling · Unsupported
- Reasoning
UnsupportedReasoning · Unsupported
- Vision
SupportedVision · Supported
- Streaming
UnsupportedStreaming · Unsupported
- JSON mode
UnsupportedJSON mode · Unsupported
USD per image
- Image input · 1K
- $0.00252
- Image input · 2K
- $0.00252
- Image output · 1K
- $0.0336
- Image output · 2K
- $0.063
- Precision
- Official precision
- Price checked
Model availability and prices
Overview
Submit a text prompt to generate images, or send a prompt and reference images for an edit. The response reports the input and output image counts separately.
- Version
- qwen-image-3.0-pro
- Input / output
- text, image / image
- Endpoint
- /v1/images/generations, /v1/images/edits
API protocols and integration
Authorization: Bearer ITERACOMPUTE_API_KEY
POST /v1/images/generationsPOST /v1/images/edits
Generate or edit PNG images. The input and output image counts are priced separately by tier.
LLMs.txt
# qwen/qwen-image-3.0-pro
Revision: c3cb831641e456ed402a686abb11d6818e34dfd2d071bd98e3934e15b55c5cab
Authorization: Bearer ITERACOMPUTE_API_KEY
POST https://api.iteracompute.com/v1/images/generations
POST https://api.iteracompute.com/v1/images/edits
- prompt · string · Describe the image or edits.
- size · string · WIDTHxHEIGHT. Total pixels must be between 262144 and 4194304.
- n · integer · Free accounts can request 1 image. Paid accounts can request 1 to 6 images per call. · [1, 6] · default=1
- image · array · One to three image references for edits, in the order used by the prompt.
- seed · integer · Random seed. · [0, 2147483647]
- watermark · boolean · Add a watermark. · default=false
Install requests and set ITERACOMPUTE_API_KEY. Generate with /images/generations. For edits use /images/edits and pass one to three ordered reference images in the JSON image array.
import os
from pathlib import Path
import requests
base = "https://api.iteracompute.com/v1"
headers = {"Authorization": "Bearer " + os.environ["ITERACOMPUTE_API_KEY"]}
payload = {
"model": "qwen/qwen-image-3.0-pro",
"prompt": "A blue paper boat on a calm lake",
"size": "512x512",
"n": 1
}
r = requests.post(base + "/images/generations", headers=headers, json=payload, timeout=600)
r.raise_for_status()
for item in r.json()["data"]:
print(item["url"])
https://www.alibabacloud.com/help/en/model-studio/qwen-image-generation-and-editing-api-referenceAPI parameters
- Generate or edit PNG images. The input and output image counts are priced separately by tier.
These parameters and ranges describe the current route. Account and context limits also apply. Parameter acceptance does not establish model capability.
- Tool calling
- Unsupported
- Reasoning
- Unsupported
- Vision
- Supported
- Streaming
- Unsupported
- JSON mode
- Unsupported
Parameters and values
Click a parameter to copy its name; scroll the table horizontally to see all columns. Usage notes identify protocol differences; identical names do not guarantee cross-endpoint support.
| Parameter | Type | Acceptance | Range | Usage / protocol |
|---|---|---|---|---|
| integer | Accepted | [1, 6] | Free accounts can request 1 image. Paid accounts can request 1 to 6 images per call. Default 1. | |
| integer | Accepted | [0, 2147483647] | Random seed. | |
| string | Accepted | — | WIDTHxHEIGHT. Total pixels must be between 262144 and 4194304. | |
| array | Accepted | — | One to three image references for edits, in the order used by the prompt. | |
| string | Accepted | — | Describe the image or edits. Required. | |
| boolean | Accepted | — | Add a watermark. Default false. |
Current configuration example
POST /v1/images/generations
{
"model": "qwen/qwen-image-3.0-pro",
"prompt": "A blue paper boat on a calm lake",
"size": "512x512",
"n": 1
}Parameter revision:c3cb831641e4
API
Install requests and set ITERACOMPUTE_API_KEY. Generate with /images/generations. For edits use /images/edits and pass one to three ordered reference images in the JSON image array.
import os
from pathlib import Path
import requests
base = "https://api.iteracompute.com/v1"
headers = {"Authorization": "Bearer " + os.environ["ITERACOMPUTE_API_KEY"]}
payload = {
"model": "qwen/qwen-image-3.0-pro",
"prompt": "A blue paper boat on a calm lake",
"size": "512x512",
"n": 1
}
r = requests.post(base + "/images/generations", headers=headers, json=payload, timeout=600)
r.raise_for_status()
for item in r.json()["data"]:
print(item["url"])Pricing
USD per image
- Model ID
qwen/qwen-image-3.0-pro- Verification scope and sources
View verification scope and sources
2026-11-21 · Verified image generation and editing, 1K and 2K charges, and key isolation through the Singapore gateway. Capacity limits were tested separately. One 2K edit combining all three references timed out.
Usage limits
- The actual output area determines the 1K or 2K billing tier.
- Free accounts can generate one image per call. Paid accounts can request up to six.
Use cases
Integration tools and guides
FAQ
How do I get started?
How is usage billed?
New arrivals
Explore the models selected for New Arrivals, with API pricing, supported capabilities and integration guides.
Qwen3.7-Plus
qwen/qwen3.7-plus
Qwen3.7-Plus returns text from text and visual input.
Launched on IteraCompute
- Input
- $0.384
- Output
- $1.536
USD / 1M tokens
Wan 3.0 Prime
wan/wan3.0-video-prime
Wan 3.0 Prime generates video from a prompt and optional reference media.
Launched on IteraCompute
Wan 3.0
wan/wan3.0-video
Wan 3.0 generates video from a prompt and optional reference media.
Launched on IteraCompute