LongCat
meituan-longcatLongCat's 2 models on ModelRunner span Image-to-Video and Text-to-Video, from $0.02 per second of video 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.
LongCat models & pricing
LongCat-Video t2v
meituan-longcat
Turn plain text into cinematic, on-brand video. Describe the scene and camera feel; LongCat generates smooth, consistent shots with adjustable length, FPS, and quality.
LongCat-Video i2v
meituan-longcat
LongCat-Video turns a single still image into minutes-long, smooth 480p, 30fps video with stable style, lighting, and identity — fast, consistent, production-ready animation from one frame.
What you can build with LongCat models
- Generate longer-form 480p video from text affordably LongCat-Video t2v
- Create extended scenes with consistent style LongCat-Video t2v
- Draft video narratives beyond short-clip limits LongCat-Video t2v
- Animate one image into minutes-long smooth 480p video LongCat-Video i2v
- Create extended ambient or scenic footage from a still LongCat-Video i2v
- Produce long background visuals for streams and events LongCat-Video i2v
Browse by capability
Call a LongCat 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/meituan-longcat/longcat-video-t2v-480p \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use LongCat models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every LongCat 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/mcpResearch, weights & licences
Frequently asked questions
What LongCat models can I run on ModelRunner?
The catalog has 2 public LongCat models: LongCat-Video t2v and LongCat-Video i2v. They cover image-to-video 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 LongCat models cost?
Pay-per-use, with no subscription: the 2 LongCat models billed per second of video 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 LongCat model from the API?
POST to https://queue.modelrunner.run/meituan-longcat/longcat-video-t2v-480p 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 LongCat models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 2 LongCat 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.
Where is the source code or paper for LongCat models?
2 of the 2 LongCat models in the catalog link their own upstream sources — LongCat-Video t2v and LongCat-Video i2v — covering some combination of code repository, paper, weights and licence. The links are listed on this page and on each model's own page.
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.