Z.ai GLM 5.3 Flash
Z.AI's GLM 5.3 Flash is a multimodal 320B-parameter (18B active) Mixture-of-Experts model. Built for developer agent workflows, visual coding, and complex tool-use tasks. The model is served without Mistral modifications.
Context
1M
Max output
128k
Price
$0.15
Input/M Tokens
$0.03
Cached input/M Tokens
$0.5
Output/M Tokens
Speed
Performance
Context
1M
Max output
128k
Price
$0.15
/M Tokens
$0.03
/M Tokens
$0.5
/M Tokens
Other Models
