Happy Horse 1.0 is now on ModelsLab

Try Now
Skip to main content
Available now on ModelsLab · Language Model

Z.ai: GLM 4.5 Air (free)Agentic Power, Free Access

Try Z.ai: GLM 4.5 Air (free)API Documentation

Run Efficient Agentic Workflows

MoE Efficiency

106B Params, 12B Active

Activates 12B of 106B parameters for high performance at low compute.

Hybrid Reasoning

Thinking and Non-Thinking Modes

Switch between complex reasoning with tools and instant responses.

Agentic Native

128K Context Window

Handles multi-step planning, tool calls, and long-context tasks seamlessly.

Examples

See what Z.ai: GLM 4.5 Air (free) can create

Copy any prompt below and try it yourself in the playground.

Code Refactor

“Analyze this Python function for efficiency issues, then rewrite it using async patterns and add unit tests. Code: def fetch_data(url): response = requests.get(url) return response.json()”

Data Pipeline

“Design a workflow to process CSV sales data: clean outliers, compute monthly trends, generate SQL insert statements, and suggest visualization code in Matplotlib.”

Logic Puzzle

“Solve this riddle step-by-step: Three houses in a row, owners A B C drink water milk tea, own cat dog bird, smoke none dunhill blends. Who owns the cat? Use thinking mode.”

API Agent

“Plan and execute: Fetch weather API for Tokyo, analyze temperature trends over 7 days, output JSON summary with forecast recommendations.”

For Developers

A few lines of code.
Agents live. Zero cost.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per token, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/llm/chat/completions",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "",
  "model_id": ""
}
)
print(response.json())

FAQ

Common questions about Z.ai: GLM 4.5 Air (free)

Read the docs

Z.ai: GLM 4.5 Air (free) is a 106B parameter MoE model with 12B active params, optimized for agentic tasks. It supports 128K context and hybrid reasoning modes. Free access via API endpoints.

Yes, Z.ai: GLM 4.5 Air (free) API provides zero-cost input/output tokens on select platforms. Integrates with OpenAI-compatible SDKs. Check provider for rate limits.

Ranks top in agentic benchmarks like τ-bench (69.4 score) and reasoning tasks. Beats Gemini 2.5 Flash on multiple evals. Excels in coding and multi-step planning.

Serves as free alternative to GPT-series for reasoning, coding, and agents. Matches proprietary models in efficiency via MoE architecture. Use for tool invocation and workflows.

Supports 128K-131K token context window. Enables long document analysis and extended agent interactions. Handles complex, multi-turn conversations.

Built for autonomous planning, tool calls, web browsing, and code execution. Powers data analysis, software dev, and business automation. Native support in thinking mode.

Ready to create?

Start generating with Z.ai: GLM 4.5 Air (free) on ModelsLab.

Try Z.ai: GLM 4.5 Air (free)API Documentation