glm-5.3-flashx

mit320B / 18B

GLM-5.3-Flash/GLM-5.3-FlashX is the first native multimodal model in the GLM-5 series, delivering stronger intelligence than GLM-5.2 at an exceptionally low cost.

Context
1M
Max output
128K
Input price
$0.37/1M tokens
Output price
$1.25/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Prompt Caching
Fine-tuning

Details

Model IDzai/glm-5.3-flashx
Familyglm-5.3
Licensemit
Status—
Typechat
Input modalitiestext, image
Output modalitiestext
Open weightYes
Parameters320B / 18B
Architecture—
Context window1M tokens
Max input—
Max output128K tokens
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.37
Output
$1.25
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: glm-5.3

ModelContextMax outPricing
glm-5.3-flash1M128K$0.04$0.07
glm-5.31M128K$0.07$1.4
glm-5.3-flashx1M128K$0.37$1.25
glm-5.3-promo-501M—$0.7$2.2
glm-5.3-fast1M—$2.1$6.6

API

GET/v1/models/vercel/zai/glm-5.3-flashx

glm-5.3-flashx

zai/glm-5.3-flashx

GLM-5.3-Flash/GLM-5.3-FlashX is the first native multimodal model in the GLM-5 series, delivering stronger intelligence than GLM-5.2 at an exceptionally low cost.

Changes · 2 entries
zai/glm-5.3-flashxcreateca7a400Nov 2, 2026, 03:02 AM
zai/glm-5.3-flashxcreate2ae168fSep 18, 2026, 06:37 AM