Models/glm-4.6

glm-4.6Active · Cloud

Novita AI · Released Sep 2025 · MIT

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

Context
205K
Max output
131K
Input
$0.55
Output
$2.20
Cached in
$0.11
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

ProviderNovita AI
ReleasedSep 2025
LicenseMIT
InputText
OutputText
Throughput-
Availability99.9%

Related models