Z.ai: GLM 4.5 Air

Public pricingIntelligence 76/100Medium memory深度思考工具调用

Z.ai: GLM 4.5 Air 是一款文本模型，适合智能体工作流与工具调用。它结合了可靠的工具调用与智能体表现、131K tokens上下文和低成本定位，可在agent workflows, tool use, and orchestration中提供可靠表现。它适合重视质量、速度与成本的团队，能带来稳定输出、灵活部署与扩展空间。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。

Input

$0.13/1M

Output

$0.85/1M

Cached

$0.03/1M

Batch

$0.10/1M

Calculate your GLM 4.5 Air bill.

Set your workload — see cost at your exact volume.

What would GLM 4.5 Air cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

GLM 4.5 Air at a glance.

Memory

131,072

tokens

Max reply

98,304

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

—

Released

Jul 2025

Training cutoff

Apr 2025

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • humanitys_last_exam

    8.12

  • swe_bench_verified

    57.6

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick GLM 4.5 Air

  • Multi-step reasoning, research agents, or hard math.
  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

GLM 4.5 Air — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, GLM 4.5 Air costs roughly $44 per month. Input is $0.13 /1M tokens and output is $0.85 /1M tokens.
GLM 4.5 Air has a 131,072-token context window (medium memory — a long report or a codebase file). That means you can fit about 24,576 words of input and history in a single call.
Beyond text generation, GLM 4.5 Air supports deep step-by-step reasoning, calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
GLM 4.5 Air was released in July 2025, with training data cut off around April 2025.
Models in a similar class include GLM 4 32B, GLM 4.7 Flash, GLM 4.6V. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare GLM 4.5 Air against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard