128K

reasoner

Chat

Zhipu AI

GLM-4.5 Air API

Zhipu’s GLM‑4.5 Air API is a RESTful endpoint on the Z.ai (global) and Zhipu AI Open (Mainland China) platforms that provides access to the compact 106 billion‑parameter (12 billion active) GLM‑4.5 Air model—featuring hybrid “thinking” and “non‑thinking” modes and full configurability of inference settings (e.g., temperature, max tokens, streaming) for efficient, high‑throughput intelligent‑agent applications .
Get Free API Key
  • Flexible Solution
  • Constant Updates 
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key="<YOUR_API_KEY>",    
)

response = client.chat.completions.create(
    model="GLM-4.5 Air",
    messages=[
        {
            "role": "system",
            "content": "You are an AI assistant who knows everything.",
        },
        {
            "role": "user",
            "content": "Tell me, why is the sky blue?"
        },
    ],
)

message = response.choices[0].message.content

print(f"Assistant: {message}")

All AI Models in One API
500+ AI Models

Free For A Limited Time! Register Now 

Get 1M Free Token Instantly！

zhipu-logo

GLM-4.5 Air API

Zhipu’s GLM-4.5 Air API is a RESTful endpoint on the Z.ai (global) and Zhipu AI Open (Mainland China) platforms that provides access to the compact 106 billion‑parameter (12 billion active) GLM‑4.5 Air model—featuring hybrid “thinking” and “non‑thinking” modes and full configurability of inference settings (e.g., temperature, max tokens, streaming) for efficient, high‑throughput intelligent‑agent applications .

Basic Features

  • Parameter Efficiency: 106 billion total parameters, 12 billion active parameters, enabling a high performance-to-size ratio .
  • Hybrid Reasoning Modes:
    • Thinking Mode for complex reasoning and tool usage.
    • Non‑thinking Mode for instant responses.
  • Open‑Source License: Released under the MIT license, permitting commercial use and secondary development .

Technical Architecture

  • Mixture-of‑Experts (MoE) design, GLM-4.5 Air share the same core approach as the full GLM‑4.5 (355 B total / 32 B active) but optimized for a compact footprint.
  • 128K Context Window: Supports long-horizon tasks such as multi‑turn dialogue and document understanding.
  • Native Function Calling: Allows seamless integration with external APIs, databases, or tool chains for agentic workflows .

Benchmark Performance

Across 12 industry-standard benchmarks spanning agentic, reasoning, and coding tasks:

  • Overall Score: 59.8 (against 63.2 for GLM‑4.5), ranking 6th among leading open‑source and proprietary models.
  • Agentic Benchmarks (e.g., BFCL v3, BrowseComp): achieves 21.3% on BrowseComp, demonstrating competitive tool‑use capabilities.
  • Reasoning & Coding (e.g., MMLU Pro, SWE‑Bench): scores up to 81.4 on MMLU Pro and 57.6 on SWE‑Bench Verified.
GLM-4.5 Air

Model Version comparison

  • GLM‑4.5: 355 B total / 32 B active — the flagship for maximum capability.
  • GLM-4.5 Air: 106 B total / 12 B active — the efficiency‑optimized sibling for resource‑sensitive deployments .

How to call GLM-4.5 Air API from CometAPI

GLM-4.5 Air API Pricing in CometAPI，20% off the official price:

  • Input Tokens: $0.16/ M tokens
  • Output Tokens: $1.07/ M tokens

Required Steps

  • Log in to cometapi.com. If you are not our user yet, please register first
  • Get the access credential API key of the interface. Click “Add Token” at the API token in the personal center, get the token key: sk-xxxxx and submit.
  • Get the url of this site: https://api.cometapi.com/

Use Method

  1. Select the “glm-4.5-air” endpoint to send the API request and set the request body. The request method and request body are obtained from our website API doc. Our website also provides Apifox test for your convenience.
  2. Replace <YOUR_API_KEY> with your actual CometAPI key from your account.
  3. Insert your question or request into the content field—this is what the model will respond to.
  4. . Process the API response to get the generated answer.

CometAPI provides a fully compatible REST API—for seamless migration. Key details to API doc:

  • Base URL: https://api.cometapi.com/v1/chat/completions
  • Model Names: “glm-4.5-air“
  • Authentication:  Bearer YOUR_CometAPI_API_KEY header
  • Content-Type: application/json .

See Also GLM‑4.5 API

Start Today

One API
Access 500+ AI Models!

Free For A Limited Time! Register Now
Get 1M Free Token Instantly！

Get Free API Key
API Docs

Related posts

How Much Does GLM 4.5 Series Cost Are they worth it
Technology

How Much Does GLM 4.5 Series Cost? Are they worth it?

2025-07-30 No comments yet

China’s Z.ai (formerly Zhipu AI) has once again seized headlines with the launch of its open‑source GLM 4.5 Series. Positioned as a cost‑efficient, high‑performance alternative to existing large language models, GLM‑4.5 promises to reshape token‑economics and democratize access for startups, enterprises, and research institutions alike. this comprehensive article explores the GLM‑4.5 Series’s origins, pricing structure, […]

Zhipu AI releases GLM-4.5 An Open Source SOTA model for Reasoning , Code & Agents
Technology

Zhipu AI releases GLM-4.5: An Open Source model for Reasoning , Code & Agents

2025-07-29 No comments yet

On July 28, 2025, Beijing‑based startup Zhipu AI officially unveiled its GLM-4.5 series of open‑source large language models, marking its most powerful release to date and targeting advanced intelligent‑agent applications. The announcement—made via a live online event following the World Artificial Intelligence Conference (WAIC)—showcased two variants: the full‑scale GLM‑4.5 with 355 billion total parameters (32 billion active) […]