model · Zhipu · open · source listing 2026-09-18
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...
Sign in to save- maker
- Zhipu
- openness
- open
- context
- 1M tokens
- price in
- $0.37 / M tokens
- price out
- $1.25 / M tokens
- input modalities
- text, image, video
- output modalities
- text
- run
- api, local
z-ai · zhipu · text · vision · video