Back to models
Zhipu AI (Z.ai)active

GLM-4.6V-FlashX

Paid, enhanced version of GLM-4.6V-Flash multimodal model with higher capacity and stability; supports native multimodal tool calling, vision-language tasks, and long-context processing

Input / 1M tokens

$0.0000

Output / 1M tokens

$0.400

Context window

128K

Capabilities

  • Streaming
  • Function Calling
  • Multimodal Tool Use
  • Vision Understanding