GLM 5.3 FlashX
GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...
The figures
- Made by
- Z.ai
- Model ID
- z-ai/glm-5.3-flashx
- Input
- $0.37 per million tokens
- Output
- $1.25 per million tokens
- Context window
- 1.05M tokens
- Longest answer
- 131K tokens
- Takes in
- text, image, video
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- No
- Released
- 18 Sept 2026
Read on 3 Oct 2026.