GLM-4.5-Air adopts a more compact design with 106B parameters.
All You Need to Know About This Model
Overview:
Model Provider:OTHERS
Model Type:Large Language Model
Deployment:Inferencing API; Playground
Pricing:$0/M Input & $0/M Output
Key Specs:
Parameters:-
Context:32k tokens
Architecture Type:-
Knowledge Cutoff:-
Core Strengths:
High efficiency optimization
Good capability retention
Cost-effective operation mode
Easy deployment process
Use Cases:
High-volume application processing
Real-time service delivery
Resource-constrained environments
Cost-sensitive project deployment
Explore Similar Models
NEW
HOT
GLM-4.7 is Z.AI’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.
LLM
GLM 4.7
202.8K CONTEXT:
Input type:
Output type:
Context:202.75K
Input:$0.44/M tokens
Output:$1.74/M tokens
Max Output:131.07K
$0.44/1.74M in/out
NEW
HOT
357B-parameter efficient MoE model from Zhipu AI.
LLM
GLM 4.6
202.8K CONTEXT:
Input type:
Output type:
Context:202.75K
Input:$0.44/M tokens
Output:$1.74/M tokens
Max Output:131.07K
$0.44/1.74M in/out
NEW
HOT
Gemini 3 Flash is Googles state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
LLM
PREVIEW
Gemini 3 Flash Preview
200.0K CONTEXT:
Input type:
Output type:
Context:200.00K
Input:$0.4/M tokens
Output:$2.4/M tokens
Max Output:65.54K
$0.4/2.4M in/out
NEW
HOT
Gemini 3 Flash is Googles state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.