All Z.ai models
Z

GLM 4.5 Air

Z.ai · released July 2025

GLM 4.5 Air is a Z.ai model with a 131K token context window — about 190 pages of text. It reads Text and replies in Text. It can show its reasoning before it answers.

$0.149

input / 1M tokens

$0.978

output / 1M tokens

131K

context — about 190 pages

0.15¢

a client proposal

Pricing

Input
$0.149 per million tokens
Output
$0.978 per million tokens
Cached input
$0.029 per million tokens

Billed from your Alyph wallet. Prices can change when the provider changes theirs — last checked August 9, 2026.

The numbers

Provider
Released
July 2025 (2025-07-25)
Context window
131K tokens — about 190 pages
Max output
98K tokens per reply
Input
Text
Output
Text
Reasoning
Shows its thinking before answering
Knowledge cutoff
2024-12-31

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output
free$0.16$0.320 tokens250k500k750k1000k
GLM 4.5 Air

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

What a task costs

2K tokens in · 500 tokens out.

GLM 4.5 Air

Z.ai

0.08¢

for this task

38% input · 62% output

Full pricing →

Your $5 welcome credit covers about 6,347 of these.

Compare GLM 4.5 Air

Closest in price on a typical task:

Questions, answered

How much does GLM 4.5 Air cost on Alyph?

GLM 4.5 Air costs $0.149 per million input tokens and $0.978 per million output tokens on Alyph. A typical task — 5K tokens in, 800 out — works out to about 0.15¢. Billed from your Alyph wallet, with hard spending limits. Prices can change when the provider changes theirs; this page was last checked on August 9, 2026.

What is GLM 4.5 Air's context window?

131K tokens — about 190 pages. Replies can be up to 98K tokens long.

Can GLM 4.5 Air read images and files?

GLM 4.5 Air is text-only. The canvas still serializes uploads into plain text, so you can work with files — but it cannot see images.

Does GLM 4.5 Air show its reasoning?

Yes. GLM 4.5 Air can expose its thinking before the final answer, so you can watch how it got there.

Test GLM 4.5 Air against Qwen3 Next 80B A3B Instruct

One prompt, both models at the same time, the better answer wins. Free to start, with $5 of credit.