glm-4.5

deprecatedmit355B / 32B

GLM-4.5 and GLM-4.5-Air are Z.AI's models, purpose-built as foundational models for agent-oriented applications. Both leverage a Mixture-of-Experts (MoE) architecture. GLM-4.5 has a total parameter count of 355B with 32B active parameters per forward pass, while GLM-4.5-Air adopts a more streamlined design with 106B total parameters and 12B active parameters.

Context
128K
Max output
96K
Input price
$0.6/1M tokens
Output price
$2.2/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Prompt Caching
Fine-tuning

Details

Model IDzai/glm-4.5
Familyglm-4.5
Licensemit
Statusdeprecated
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters355B / 32B
Architecturemoe
Context window128K tokens
Max input—
Max output96K tokens
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.6
Output
$2.2
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: glm-4.5

ModelContextMax outPricing
glm-4.5-air128K—$0.2$1.1
glm-4.5128K96K$0.6$2.2
glm-4.5v66K16K$0.6$1.8

API

GET/v1/models/vercel/zai/glm-4.5