← all models

GLM 5.3 FlashX

z.ai

openrouter
Parameters — not published
Context 1M 1048576 tokens
Input $0.37 OpenRouter
Output $1.25 OpenRouter
Cache read $0.08 OpenRouter

Accepts

text image video

Capabilities

include_reasoning max_tokens reasoning reasoning_effort response_format structured_outputs temperature tool_choice tools top_k top_p

Description

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 OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter z-ai/glm-5.3-flashx version slug z-ai/glm-5.3-flashx-20260918 name Z.ai: GLM 5.3 FlashX display name GLM 5.3 FlashX

Identifiers

Vendor
z.ai
OpenRouter
z-ai/glm-5.3-flashx
Version slug
z-ai/glm-5.3-flashx-20260918
Released
2026-09-18T15:07:00.000Z
First seen
59 d ago
Last crawled
17 min ago