GLM-4.5-Air pricing & specs

Z.AI (Zhipu) · released 2025-07-28 · ● verified 2026-10-11

input / 1M$0.20
output / 1M$1.10
context131.1K
max output98.3K

// price history ($/1M tokens)

$1.265
input $/1Moutput $/1M2025-07-28 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs GLM-4.5-Air
Gemma 4 E2B IT$0.04$0.08131.1K−88.2%
Qwen3.7 Flash$0.03$0.131M−87.1%
Qwen Turbo$0.05$0.201M−79.4%
DeepSeek V4 Flash 0731$0.06$0.181.05M−78.8%
GPT OSS 120B$0.05$0.25131.1K−76.5%

// price by host

hostin $/1Mout $/1M
Novita AI$0.13$0.85

// faq

How much does GLM-4.5-Air cost?

GLM-4.5-Air costs $0.20 per million input tokens and $1.10 per million output tokens. At 50M input and 10M output tokens per month that is about $21.00.

What is the context window of GLM-4.5-Air?

131.1K tokens, with up to 98.3K output tokens per request.

Does GLM-4.5-Air support prompt caching?

Yes. Cached input tokens cost $0.03 per million and cache writes cost $0 per million.

What are cheaper alternatives to GLM-4.5-Air?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.

Is GLM-4.5-Air open weights?

Yes. It is available from 1 tracked hosts; the cheapest is Novita AI at $0.13 input and $0.85 output per million tokens.

// spec sheet

input / 1M
$0.20
output / 1M
$1.10
cache read / 1M
$0.03
cache write / 1M
$0
blended (3:1)
$0.425
context
131.1K
max output
98.3K
input types
text
reasoning
yes
tool calling
yes
structured output
no
open weights
yes
knowledge cutoff
2025-04
price source
Z.AI (Zhipu)

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Qwen3.7 Flash$0.03$0.13$2.80
Qwen Turbo$0.05$0.20$4.50
GLM-4.5-Air$0.20$1.10$21.00

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.