GLM API and MCP: how to connect the code models to your project

GLM is a family of chat models for code and text. NeuralSpace offers the following models: GLM-5.3 Flash, GLM-5.3. 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.

What GLM can do

GLM models are built for vibe coding and text tasks. GLM-5.3 Flash is the fast version for high-volume requests, GLM-5.3 is the full version for complex code and reasoning. Both write and explain code, answer questions and hold conversations.

API endpoint

Send a request to POST /v1/chat/completions. Example: {"model": "glm-5.3", "messages": [{"role": "user", "content": "Review this code"}]}. Authorization uses an API key in the x-api-key header. Available model ids: glm-5.3-flash, glm-5.3.

MCP tools

The NeuralSpace MCP server is available at POST /mcp (Streamable HTTP). To work with GLM, an agent uses the tools: chat, 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

How does Flash differ from the full version?

Flash is faster and cheaper, the full version is more powerful for hard tasks.

Is it good for vibe coding?

Yes, both versions are tuned for code generation and explanation.

What format is the request?

OpenAI-compatible: POST /v1/chat/completions.