Use Qwen Image 3.0 Pro with Comfy Router

Call qwen/qwen-image-3.0-pro through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for qwen/qwen-image-3.0-pro, served by Comfy Router from Qwen.

Quick start

Create a key at platform.comfy.org/profile/api-keys and export it as COMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk, npm install @comfyorg/sdk); the cURL snippet is the same call over raw HTTP.

Model ID: qwen/qwen-image-3.0-pro

Endpoint: POST https://api.comfy.org/v2/models/qwen/qwen-image-3.0-pro

Python

from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment. Each call sends a fresh
# Idempotency-Key and waits up to 10 minutes for the finished result.
with Comfy() as client:
    result = client.models.run(
        "qwen/qwen-image-3.0-pro",
        {
            "input": {
                "messages": [
                    {
                        "content": [
                            {
                                "text": "A single red maple leaf on a plain white background.",
                            },
                        ],
                        "role": "user",
                    },
                ],
            },
        },
    )

print(result)

Schema

Input

input · object · required

The input parameter object containing the request messages

input.messages · object[] · required

The request content array. Only single-round conversations are supported, so the array must contain exactly one object

input.messages[].content · object[] · required

The message content array. Text-to-image contains one text object; image editing contains 1-3 image objects and one text object

input.messages[].content[].image · string

The URL or Base64 encoded data of an input image. 1-3 images are supported for image editing

input.messages[].content[].text · string

The positive prompt that describes the image content, style, and composition to generate or edit

input.messages[].role · string · required

The role of the message sender. Must be set to user

Possible values: user

model · string

The ID of the model to call for multimodal image generation and editing. Available values are qwen-image-3.0-pro and qwen-image-3.0. It is NOT in this schema’s required list because Comfy Router fills it from the {model} path segment of /v2/models/qwen/{model}, so a Router caller omits it; a direct v1 call to the /proxy/ route must supply it.

parameters · object

Additional parameters to control image generation

parameters.n · integer · default: "1"

The number of output images. Range 1-6, default is 1

Range: 1 to 6

parameters.negative_prompt · string

The negative prompt that describes content you do not want to appear in the image

parameters.prompt_extend · boolean · default: "true"

Whether to enable intelligent prompt rewriting. Default is true

parameters.prompt_extend_mode · string · default: "\"direct\""

The prompt rewriting method, direct (default, supported for T2I and I2I) or agent (T2I only)

Possible values: direct, agent

parameters.seed · integer

Random number seed to control randomness. Range [0, 2147483647]

Range: 0 to 2147483647

parameters.size · string

The output image resolution in the format widthheight, for example 10241024. The API accepts a pixel area between 262144 (512512) and 6553600 (25602560) with an aspect ratio between 1:8 and 8:1. If not specified, the model automatically recommends a resolution based on the prompt

parameters.watermark · boolean · default: "false"

Whether to add a watermark. Default is false

Generated from the schema Router serves at GET /v2/models/qwen/qwen-image-3.0-pro/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

code · string

The error code for the failed request (not returned if request is successful)

message · string

Detailed information about the failed request (not returned if request is successful)

output · object

Contains the model generation results

output.choices · object[]

The list of result options

output.choices[].finish_reason · string

The reason why the task stopped. The value is stop when the task completes normally

output.choices[].message · object

The message returned by the model

output.choices[].message.content · object[]

The message content containing the generated image information

output.choices[].message.content[].image · string

The URL of the generated image in PNG format. The link is valid for 24 hours

output.choices[].message.content[].text · string

A textual element returned in place of an image. An element carrying only this field produced NO asset, so a caller keys completion off image rather than off the presence of a content element

output.choices[].message.role · string

The role of the message. Fixed as assistant

request_id · string

Unique request identifier

usage · object

The resource usage of this call. Only returned on success

usage.input_image_count · integer

The number of input images in the request. Returns 0 for text-to-image

usage.input_image_type · string

The input image billing tier, qima_input_1k or qima_input_2k, determined by the output resolution pixel area

usage.output_height · integer

The height of the final output image in pixels

usage.output_image_count · integer

The actual number of output images returned

usage.output_image_type · string

The output image billing tier, qima_output_1k or qima_output_2k, determined by the output resolution pixel area

usage.output_width · integer

The width of the final output image in pixels

Examples

Input

{
  "input": {
    "messages": [
      {
        "content": [
          {
            "text": "A single red maple leaf on a plain white background."
          }
        ],
        "role": "user"
      }
    ]
  }
}

Output

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "content": [
            {
              "image": "https://example.invalid/qwen/generated.png"
            }
          ],
          "role": "assistant"
        }
      }
    ]
  },
  "request_id": "9f2c1b3a-5d4e-4a67-8b90-1c2d3e4f5a6b",
  "usage": {
    "input_image_count": 0,
    "output_height": 512,
    "output_image_count": 1,
    "output_image_type": "qima_output_1k",
    "output_width": 512
  }
}

Before you ship

The snippets above are the shortest working call. Three things are the same for every model and are documented once on the Comfy Router headers page: send an Idempotency-Key on every paid call and reuse it when you retry, expect the connection to be held up to Router’s 10 minute deadline, and keep X-Comfy-Request-Id from every response. The SDKs do all three for you; the cURL tab does none of them. On failure, X-Comfy-Error-Type names the bucket, and a 422 means the body failed the model’s schema and was never billed.

Headers

Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

Quick Start

Typed error handling in Python and TypeScript, reading the 422, walking the catalog.

Limitations

What Router does not do today, and what to use instead.