glm-5.2

mit

GLM-5.2 is a flagship model built for the era of long-horizon tasks. With truly usable 1M-token context, it has been tested to handle project-scale engineering context, delivering more stable long-task execution, more reliable adherence to engineering standards, and higher success rates in development scenarios. A single task can complete the full development workflow—from requirements to deployable products across multiple platforms.

Context
1M
Max output
128K
Input price
$0/1M tokens
Output price
$0/1M tokens

Capabilities

vision
tool call
structured output
reasoning
json mode
streaming
fine tuning
batch

Details

Model IDzai/glm-5.2
Familyglm-5.2
Licensemit
Parameters
Status
Input modalitiestext
Output modalitiestext
Architecture
Knowledge cutoff
Training data cutoff
Release date
Deprecation date
Typechat
Reasoning tokens
Max input
Open weightYes
Prompt cachingSupported
Sourceofficial
Last updated

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0
↓100%$0.8
Output
$0
↓100%$2.52
Cache write
Cache read
Batch in
Batch out
Price history · $/1M input
$1.4
$0.95
$0.9
$0.8
$0
Jun 18Jun 30Jul 17Jul 31Aug 17
DateInputOutputChange
Jun 18, 2026$1.4$4.4
Jun 30, 202688d97e5$0.95$3↓32%
Jul 17, 202620c73ac$0.9$2.84↓5%
Jul 31, 202639b8745$0.8$2.52↓11%
Aug 17, 2026be35184$0$0↓100%

Input is ↓100% since Jun 18, 2026, from $1.4 to $0 per 1M tokens.

Family Comparison: glm-5.2

ModelContextMax outPricing
glm-5.21M128K$0$0
glm-5.2-fast1M$2.1$6.6

API

GET/v1/models/vercel/zai/glm-5.2