GLM 5.3 Fast

GLM-5.3-Prime is a faster version of GLM-5.3. It keeps all of the original model's capabilities while generating output 1.5 to 2 times faster, thanks to inference acceleration.

scx-ai-gp/glm-5.3-fast
STABLEGet Started
Streaming
No ratings yetSign in to rate

Select Provider

SCX.ai Pricing for GLM 5.3 Fast

View detailed pricing and capabilities for this provider.

Context: 1M
Input
$2.8
/M tokens
Cache Read
$0.56
/M tokens
Output
$8.8
/M tokens
Get Started