Z.ai
z-aiAll 2 Z.ai models in the ModelRunner catalog are Text-to-Text endpoints — low-latency coding assistant: fast inline completions while a developer waits.
2 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
Z.ai models & pricing
GLM-5.2 Fast Preview
z-ai
Low-latency chat completions from the GLM-5.2 weights on throughput-tuned serving — consistently faster than the standard tier, at twice the price and identical answer quality.
GLM-5.2
z-ai
Open-weight (MIT) thinking model for agentic coding and long-horizon reasoning, with a 1M-token context, seven levels of thinking effort, tool calling and streaming over an OpenAI-compatible chat endpoint.
What you can build with Z.ai models
- Low-latency coding assistant: fast inline completions while a developer waits GLM-5.2 Fast Preview
- Speed up an agent loop that makes many sequential model calls GLM-5.2 Fast Preview
- Real-time streaming chat where response time matters more than token cost GLM-5.2 Fast Preview
- Agentic coding: multi-step bug fixing and refactoring at high throughput GLM-5.2 Fast Preview
- Long-context code review across an entire repository in one prompt GLM-5.2 Fast Preview
- Agentic coding: multi-step bug fixing, refactoring and terminal tasks GLM-5.2
- Open-weight MIT model when a closed frontier model is not an option GLM-5.2
- Dial thinking effort up or down to trade answer quality against cost GLM-5.2
Browse by capability
Call a Z.ai 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/z-ai/glm-5.2-fast-preview \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use Z.ai models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every Z.ai 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 Z.ai models can I run on ModelRunner?
The catalog has 2 public Z.ai models: GLM-5.2 Fast Preview and GLM-5.2. They cover text-to-text. Each one has its own page with a free playground, the full input schema, and copy-paste code.
How much do Z.ai models cost?
Pay-per-use, with no subscription: each Z.ai page publishes its own rate, and you pay only for what you generate from prepaid credits.
How do I call a Z.ai model from the API?
POST to https://queue.modelrunner.run/z-ai/glm-5.2-fast-preview 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 Z.ai models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 2 Z.ai 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 Z.ai models?
2 of the 2 Z.ai models in the catalog link their own upstream sources — GLM-5.2 Fast Preview and GLM-5.2 — 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.