Wan API and MCP: how to add video generation to your project

Wan is a video generation model. NeuralSpace offers the following models: Wan 2.6. They all run through a single public API, and there is a ready MCP server for AI agents. The key is issued on the API keys page. Below are the model capabilities, request examples and setup steps.

What Wan can do

Wan 2.6 generates video from text, priced by duration (5, 10 or 15 seconds) and resolution (720p or 1080p). It supports text-to-video and image-to-video via image_urls. It suits landscapes, objects and scenes with motion.

API endpoint

Send a request to POST /v1/videos/generations. Example: {"model": "wan-2.6", "prompt": "a drone flying over a forest", "duration": 5, "resolution": "1080p"}. Authorization uses an API key in the x-api-key header. Available model ids: wan-2.6.

MCP tools

The NeuralSpace MCP server is available at POST /mcp (Streamable HTTP). To work with Wan, an agent uses the tools: generate_video, check_video, list_models, get_balance. This lets Claude Code, Cursor and other MCP clients use the site models directly.

How to connect

Sign up on NeuralSpace, open the API keys page and create an nsk-… key. Then pass it in the request header or in your MCP client settings. Full documentation is on the the /v1/docs page.

FAQ

Which durations are available?

5, 10 and 15 seconds.

Does it support references?

Yes, image-to-video via image_urls.

What format is the request?

POST /v1/videos/generations with model and prompt fields.