Back to all models

GLM-5.2

Zhipu GLM-5.2 flagship model for long-horizon coding and agentic engineering tasks with a 1M context window.

glm-5.2
STABLEGet StartedView uptime
1,048,576 context
Starting at $0.55/M input tokens
Starting at $1.93/M output tokens
Streaming
Tools
Reasoning
JSON Output

Select Provider

All Providers for GLM-5.2

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Z AI
Context: 1M
Input
$1.4
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens
+ $0.010 per search
Get Started
CanopyWave
Context: 200k
Input
$1.4
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens
Get Started
EmberCloud
Context: 203k
Input
$1.26
/M tokens
Cached
$0.234
/M tokens
Output
$3.96
/M tokens
Get Started
granite
Context: 1M
Deactivated since Jul 27, 2026
Input
$1.4
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens
Get Started
ByteDance
Context: 1.0M
Input
$1.4
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens
Get Started
Alibaba Cloud
Context: 1M
Input
$1.4
/M tokens
Cached
$0.28
/M tokens
Output
$4.4
/M tokens
Get Started
runware
Context: 1.0M
Input
$0.8
/M tokens
Cached
$0.16
/M tokens
Output
$2.55
/M tokens
Get Started
Nebius AI
Context: 1.0M
Input
$1.4
/M tokens
Cached
—
/M tokens
Output
$4.4
/M tokens
Get Started
scx-ai-gp
Context: 1M
Input
$0.55
/M tokens
Cached
$0.1375
/M tokens
Output
$1.9255
/M tokens
Get Started