Context
1.0M
Input
$0.45/M
Output
$1.50/M
Aliases:glm5.3-flashglm-53-flashzhipu-glm-5.3-flash
Z-AI's first natively multimodal GLM-5 model: image and PDF input on a 1M-token context at flash pricing. Reasoning is always on (low/high/max), with function calling and implicit prompt caching.
modal/glm-5.3-flashQuantUnspecified
- Input
- $0.45/M
- Output
- $1.50/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.09/M
- Cache write
- $0.45/M
- Thinking out
- $1.50/M