> ## Documentation Index > Fetch the complete documentation index at: https://docs.mixroute.ai/llms.txt > Use this file to discover all available pages before exploring further. # Qwen Image > Qwen Image image generation fields, model constraints, and request examples. Qwen image generation uses two request formats depending on the model. Both call the same MixRoute endpoint; do not mix input.prompt with input.messages. `POST https://api.mixroute.ai/v1/images/generations` ## Model Selection | Models | Input Format | Image URLs | | -------------------------------------------------------- | ---------------- | ------------------------------------------ | | `qwen-image`, `qwen-image-plus` | `input.prompt` | `output.results[].url` | | `qwen-image-2.0`, `qwen-image-2.0-pro`, `qwen-image-max` | `input.messages` | `output.choices[].message.content[].image` | For reference-image editing, use the [Qwen Image editing](/en/api-reference/endpoint/qwen-image-edit) page and the qwen-image-edit\* models. These request formats do not add a metadata or asset wrapper. ## Basic Text-to-Image Use qwen-image or qwen-image-plus. The input object contains prompt, not messages. ### Parameters | Field | Type | Required | Description | | ----------------- | ------- | -------- | ------------------------------------------------------------------------------------------------------- | | `model` | string | Yes | Complete model ID from the applicable model table. | | `input` | object | Yes | Input object. | | `input.prompt` | string | Yes | Text prompt. Chinese and English may be combined. Describe the desired content, style, and composition. | | `parameters` | object | No | Optional generation settings. | | `parameters.size` | string | No | Dimensions written as `width*height`, such as `1024*1024` or `1664*928`. Use an asterisk, not x. | | `parameters.n` | integer | No | Only `1` is supported per request. Make separate requests for multiple images. | ### Request Examples Set your MixRoute key in the `MIXROUTE_API_KEY` environment variable. ```bash theme={null} curl --request POST "https://api.mixroute.ai/v1/images/generations" \ --header "Authorization: Bearer $MIXROUTE_API_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "qwen-image-plus", "input": { "prompt": "A clean product photograph of a red ceramic mug on a white background." }, "parameters": { "size": "1024*1024", "n": 1 } }' ``` ```python theme={null} import json import os import requests payload = json.loads(r''' { "model": "qwen-image-plus", "input": { "prompt": "A clean product photograph of a red ceramic mug on a white background." }, "parameters": { "size": "1024*1024", "n": 1 } } ''') response = requests.post( "https://api.mixroute.ai/v1/images/generations", headers={"Authorization": "Bearer " + os.environ["MIXROUTE_API_KEY"]}, json=payload, timeout=180, ) response.raise_for_status() result = response.json() output = result.get("output") or {} if output.get("task_status") != "SUCCEEDED": raise RuntimeError(result.get("message") or result) image_urls = [item["url"] for item in output.get("results", []) if item.get("url")] if not image_urls: raise RuntimeError(result.get("message") or result) for url in image_urls: print(url) ``` ### Response A successful result has output.task\_status="SUCCEEDED". Read temporary image URLs from output.results\[].url and save the images promptly; usage.image\_count is the actual output count. ```json theme={null} { "output": { "task_status": "SUCCEEDED", "results": [ { "url": "https://example.com/generated.png" } ] }, "usage": { "image_count": 1 } } ``` ## Multimodal-Format Text-to-Image Use qwen-image-2.0, qwen-image-2.0-pro, or qwen-image-max with one user message and one text block. The request uses the multimodal envelope, but these models are listed here for text-only generation. ### Parameters | Field | Type | Required | Description | | --------------------------------- | ------- | ----------------- | ----------------------------------------------------------------------------------------------------------- | | `model` | string | Yes | Complete model ID from the applicable model table. | | `input` | object | Yes | Input object. | | `input.messages` | array | Yes | Exactly one user message. | | `input.messages[].role` | string | Yes | Must be `user`. | | `input.messages[].content` | array | Yes | One text block for text-to-image. Do not include reference images for the generation models listed here. | | `input.messages[].content[].text` | string | Per content block | Prompt text in the text block. | | `parameters` | object | No | Optional generation settings. | | `parameters.size` | string | No | Dimensions written as `width*height`, such as `1024*1024` or `1664*928`. Use an asterisk, not x. | | `parameters.n` | integer | No | Only `1` is supported per request. Make separate requests for multiple images. | | `parameters.seed` | integer | No | Random seed. Reusing a prompt and seed can give similar results; it is not a guarantee of identical output. | | `parameters.watermark` | boolean | No | Whether to add a watermark. | | `parameters.negative_prompt` | string | No | Elements to avoid in the generated image. | | `parameters.prompt_extend` | boolean | No | Whether to let the upstream service expand the prompt with additional detail. | ### Request Examples ```bash theme={null} curl --request POST "https://api.mixroute.ai/v1/images/generations" \ --header "Authorization: Bearer $MIXROUTE_API_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "qwen-image-2.0-pro", "input": { "messages": [ { "role": "user", "content": [ { "text": "A clean product photograph of a red ceramic mug on a white background." } ] } ] }, "parameters": { "size": "1024*1024", "n": 1, "seed": 42 } }' ``` ```python theme={null} import json import os import requests payload = json.loads(r''' { "model": "qwen-image-2.0-pro", "input": { "messages": [ { "role": "user", "content": [ { "text": "A clean product photograph of a red ceramic mug on a white background." } ] } ] }, "parameters": { "size": "1024*1024", "n": 1, "seed": 42 } } ''') response = requests.post( "https://api.mixroute.ai/v1/images/generations", headers={"Authorization": "Bearer " + os.environ["MIXROUTE_API_KEY"]}, json=payload, timeout=180, ) response.raise_for_status() result = response.json() output = result.get("output") or {} image_urls = [ part["image"] for choice in output.get("choices", []) for part in choice.get("message", {}).get("content", []) if part.get("image") ] if not image_urls: raise RuntimeError(result.get("message") or result) for url in image_urls: print(url) ``` ### Response Read image URLs from output.choices\[].message.content\[].image. usage.image\_count, usage.height, and usage.width describe the output. Do not parse this response with the basic interface's output.results path. ```json theme={null} { "output": { "choices": [ { "message": { "role": "assistant", "content": [ { "image": "https://example.com/generated.png" } ] } } ] }, "usage": { "image_count": 1, "height": 1024, "width": 1024 } } ``` ## Errors HTTP 400 indicates invalid parameters, such as an empty prompt, unsupported size, or unknown model. HTTP 429 indicates rate or concurrency limits; reduce request frequency before retrying.