MiniMax
minimaxMiniMax's 3 models on ModelRunner span Image-to-Video, Sound and Text-to-Video, from $0.017 per second of video upward.
3 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
MiniMax models & pricing
MiniMax Hailuo-02 Standard Image-to-Video
minimax
Animate a still image into a short, cinematic 6s or 10s video from a text prompt, with a choice of 512P or 768P output.
MiniMax Hailuo-02 Standard Text-to-Video
minimax
Generate a short, cinematic 768p video from a text prompt with smooth, lifelike motion and strong prompt adherence.
MiniMax Speech-02 HD
minimax
Turn text into natural, high-fidelity speech in 30+ languages with 300+ voices plus emotion, speed, pitch, and volume control.
What you can build with MiniMax models
- Turn a photo into a short video with natural motion MiniMax Hailuo-02 Standard Image-to-Video
- Animate a still image or illustration into a cinematic clip MiniMax Hailuo-02 Standard Image-to-Video
- Add camera movement and motion to a product or portrait shot MiniMax Hailuo-02 Standard Image-to-Video
- Bring a keyframe to life for social or hero video content MiniMax Hailuo-02 Standard Image-to-Video
- Generate a 6s or 10s video from an image and a motion prompt MiniMax Hailuo-02 Standard Image-to-Video
- Generate short cinematic clips from text affordably MiniMax Hailuo-02 Standard Text-to-Video
- Create social media video content from prompts MiniMax Hailuo-02 Standard Text-to-Video
- Prototype video ideas before production MiniMax Hailuo-02 Standard Text-to-Video
Browse by capability
Call a MiniMax 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/minimax/hailuo-02/standard/image-to-video \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use MiniMax models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every MiniMax 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 MiniMax models can I run on ModelRunner?
The catalog has 3 public MiniMax models: MiniMax Hailuo-02 Standard Image-to-Video, MiniMax Hailuo-02 Standard Text-to-Video and MiniMax Speech-02 HD. They cover image-to-video, sound 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 MiniMax models cost?
Pay-per-use, with no subscription: the 2 MiniMax models billed per second of video start at $0.017, 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 MiniMax model from the API?
POST to https://queue.modelrunner.run/minimax/hailuo-02/standard/image-to-video 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 MiniMax models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 3 MiniMax 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.