Skip to content

GLM 4.5 Air

GLM 4.5 Air is Z.ai's efficiency-focused model released July 28, 2025. It delivers fast inference for high-volume workloads while keeping reasoning and coding capability at reduced cost compared to the full GLM-4.5.

ReasoningTool UseImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'zai/glm-4.5-air',
prompt: 'Why is the sky blue?'
})

More models by Z.ai

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
205K
0.8s
46tps
$1.40/M$4.40/M
Read:$0.26/M
Write:
deepinfra logo
fireworks logo
novita logo
+1
04/07/2026
203K
1.1s
29tps
$1.20/M$4.00/M
Read:$0.24/M
Write:
zai logo
03/15/2026
203K
0.6s
62tps
$0.80/M$2.56/M
Read:$0.16/M
Write:
bedrock logo
deepinfra logo
fireworks logo
+3
02/12/2026
205K
0.1s
444tps
$2.25/M$2.75/M
Read:$2.25/M
Write:
bedrock logo
cerebras logo
deepinfra logo
+2
12/22/2025
205K
0.4s
62tps
$0.60/M$2.20/M
Read:$0.11/M
Write:
baseten logo
deepinfra logo
novita logo
+1
09/30/2025
200K
0.1s
140tps
$0.07/M$0.40/M
Read:$0.01/M
Write:
bedrock logo
zai logo