Grok Imagine API and MCP: how to add video generation to your project

Grok Imagine (video) is a video generation model. NeuralSpace offers the following models: Grok Imagine. 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 Grok Imagine (video) can do

Grok Imagine generates video from a text description. Resolutions 480p and 720p are available, the minimum duration is 6 seconds, and billing is per second. Generation is asynchronous: poll the status via GET /v1/videos/generations/:id.

API endpoint

Send a request to POST /v1/videos/generations. Example: {"model": "grok-imagine", "prompt": "a futuristic city at night", "resolution": "720p"}. Authorization uses an API key in the x-api-key header. Available model ids: grok-imagine.

MCP tools

The NeuralSpace MCP server is available at POST /mcp (Streamable HTTP). To work with Grok Imagine (video), 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 resolutions are available?

480p and 720p.

What is the minimum duration?

6 seconds, billed per second.

What format is the request?

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