Models/glm-4.5

glm-4.5Active · Cloud

Z.AI (Zhipu AI) · Released Jul 2025 · MIT

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

Context
128K
Max output
32K
Input
$0.60
Output
$2.20
Cached in
-
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Details

ReleasedJul 2025
LicenseMIT
InputText
OutputText
Throughput-
Availability100%

Related models