GLM 4.5 Air

Zhipu AI chatreasoningtool_use

API ID: z-ai/glm-4.5-air

Input Price
$0.05
/1M tokens
Output Price
$0.22
/1M tokens

About GLM 4.5 Air

GLM 4.5 Air is a budget-friendly general-purpose model from Zhipu AI with long context (131k), suitable for conversations, content creation, and general AI tasks.

๐Ÿ’ฐ
Price Ranking
#622 lowest price among 950 Chat models

Model Specifications

Context Length
131k
Max Output
98k
Release Date
2025-07-25
Capabilities
chat reasoning tool_use
Input Modalities
text
Output Modalities
text

Best For

  • Complex reasoning, math problems, multi-step logic
  • Conversations, content writing, general assistance

Consider Alternatives For

  • Image understanding (needs vision capability)
  • Simple Q&A (cheaper models available)

๐Ÿ’ฐ Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$0.09
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$2.73
/month
1000 tickets/day, ~800 tokens each
Data Analysis Pipeline
$3.77
/month
500 analyses/day, ~2k tokens each

Zhipu AI Model Lineup

Compare all models from Zhipu AI to find the best fit

Model Input Output Context Capabilities
GLM 4.5 Air Current Free Free 131k chat reasoning tool_use
GLM 4 9B Free Free 32k chat
GLM 4 9B Free Free 32k chat
GLM 4 32B Free Free 33k chat
GLM 4 32B Free Free 33k chat
GLM 4.1V 9B Thinking Free Free 66k chat vision reasoning

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Mistral Devstral 2 2512
Input: $0.05
Output: $0.22
Context: 262k
Alibaba Qwen Qwen2.5 VL 32B Instruct
Input: $0.05
Output: $0.22
Context: 128k
Alibaba Qwen Qwen3 14B
Input: $0.05
Output: $0.22
Context: 41k
Nous Research Hermes 2 Pro - Llama-3 8B
Input: $0.14
Output: $0.14
Context: 8k

๐Ÿš€ Quick Start

Get started with GLM 4.5 Air API

OpenAI-compatible SDK
from openai import OpenAI

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

response = client.chat.completions.create(
    model="z-ai/glm-4.5-air",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)