Alibaba
alibabaAlibaba's 5 models on ModelRunner span Image-to-Video, Text-to-Image, Text-to-Text and 1 more, from $0.14 per second of video upward.
5 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
Alibaba models & pricing
Qwen3.8-Max
alibaba
Answer questions about images, video and text in one chat model, with thinking effort adjustable from fully off to maximum and a 1,000,000-token context.
Qwen-Image 3.0
alibaba
Generate an image from a text prompt, with in-image text rendered natively in 12 languages and legible down to around 10px.
Happy Horse 1.1 Reference to Video
alibaba
Generate a 3-15 second video from up to nine reference photos, addressing each one positionally in the prompt so a specific character, product or prop stays recognizable in the shot.
Happy Horse 1.1 Image to Video
alibaba
Animate a still photo into a 3-15 second video at 720P or 1080P, with audio generated alongside the picture and the output frame shape taken straight from your image.
Happy Horse 1.1 Text to Video
alibaba
Generate a short video with synchronized native audio from a text prompt, with spoken dialogue lip-synced on screen, at 720P or 1080P.
What you can build with Alibaba models
- Ask questions about a screenshot, chart or photo and get a written answer Qwen3.8-Max
- Describe or summarise what happens in a video clip Qwen3.8-Max
- Agentic coding: multi-step debugging, refactoring and terminal tasks Qwen3.8-Max
- Turn thinking off for fast cheap answers, or dial it up for hard problems Qwen3.8-Max
- Read a whole codebase or document set in one million-token prompt Qwen3.8-Max
- Text to image: generate a picture from a written description Qwen-Image 3.0
- Render legible text inside an image - signs, labels, book covers Qwen-Image 3.0
- Design posters, banners and album covers with readable typography Qwen-Image 3.0
Browse by capability
Call a Alibaba 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/alibaba/qwen3.8-max \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use Alibaba models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every Alibaba 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 Alibaba models can I run on ModelRunner?
The catalog has 5 public Alibaba models: Qwen3.8-Max, Qwen-Image 3.0, Happy Horse 1.1 Reference to Video and 2 more. They cover image-to-video, text-to-image, text-to-text and text-to-video. Each one has its own page with a free playground, the full input schema, and copy-paste code.
How much do Alibaba models cost?
Pay-per-use, with no subscription: the 3 Alibaba models billed per second of video start at $0.14, 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 Alibaba model from the API?
POST to https://queue.modelrunner.run/alibaba/qwen3.8-max 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 Alibaba models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 5 Alibaba 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.