qwen/qwen-image-3.0-pro, served by Comfy Router from Qwen.
Input: Text, Image · Output: Image
Quick start
Create a key in your Comfy workspace and export it asCOMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk and 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
- Wait for the result
- Queue and collect later
The same body, sent to
POST https://api.comfy.org/v2/models/qwen/qwen-image-3.0-pro/requests. Router answers 201 with a request_id as soon as the run is admitted, and the result is collected once it is ready, from this process or another one. Queued delivery walks through status, cancellation and collection.Schema
Input
The request content array. Only single-round conversations are supported, so the array must contain exactly one object
The message content array. Text-to-image contains one text object; image editing contains 1-3 image objects and one text object
The positive prompt that describes the image content, style, and composition to generate or edit
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.The prompt rewriting method, direct (default, supported for T2I and I2I) or agent (T2I only)Possible values:
direct, agentThe 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
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
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 elementThe input image billing tier, qima_input_1k or qima_input_2k, determined by the output resolution pixel area
The output image billing tier, qima_output_1k or qima_output_2k, determined by the output resolution pixel area
Examples
Input
Output
Before you ship
The SDKs create anIdempotency-Key and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.
When a request fails, Router sends an X-Comfy-Error-Type response header explaining why. A 422 means Router rejected the input before calling the provider, and a 413 means the request body was larger than Router accepts. Download generated assets promptly because result URLs can expire.
Any size limit named in a field description above is the provider’s own bound on that field, quoted from the provider’s specification. Router applies a separate cap to the whole request body, which base64-encoded media counts against: see request body size.
This page documents one partner model called through Comfy Router. The same comfy-sdk / @comfyorg/sdk package also ships a second client, for running a whole ComfyUI workflow graph on Comfy Cloud: Comfy(api_key=...) / new Comfy({ apiKey }), with client.workflows, client.assets and client.jobs. See Comfy SDKs.
Headers
Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.
Using the Router API
Model discovery, validation errors, retries, and billing.
Limitations
What Router does not do today, and what to use instead.