Qwen
qwenQwen's 2 models on ModelRunner span Image-to-Image and Text-to-Image, from $0.02 per megapixel upward.
2 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
Qwen models & pricing
Qwen-Image-Edit
qwen
Edit an existing image from a text instruction — recolor, restyle, swap backgrounds, add or remove elements — with accurate, legible in-image text in English and Chinese.
Qwen-Image
qwen
Generate high-quality images from a text prompt, with standout accurate, legible in-image text in English and Chinese.
What you can build with Qwen models
- Edit photos with text instructions — recolor, restyle, swap objects Qwen-Image-Edit
- Change backgrounds or add elements by describing them Qwen-Image-Edit
- Make targeted local edits without masks Qwen-Image-Edit
- Generate images with accurate, legible text rendering Qwen-Image
- Create posters, banners, and signage with in-image typography Qwen-Image
- Produce multilingual text-in-image designs Qwen-Image
Browse by capability
Call a Qwen model in one request
Every endpoint shares the same lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/qwen/qwen-image-edit \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use Qwen models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every Qwen model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What Qwen models can I run on ModelRunner?
The catalog has 2 public Qwen models: Qwen-Image-Edit and Qwen-Image. They cover image-to-image and text-to-image. Each one has its own page with a free playground, the full input schema, and copy-paste code.
How much do Qwen models cost?
Pay-per-use, with no subscription: the 2 Qwen models billed per megapixel start at $0.02, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a Qwen model from the API?
POST to https://queue.modelrunner.run/qwen/qwen-image-edit with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run Qwen models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 2 Qwen models become tools your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.