GLM-5.3-FLASH

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
$0.15/1M tokens
Output price
$0.5/1M tokens

Capabilities

vision
tool call
structured output
reasoning
json mode
streaming
fine tuning
batch

Details

Creator zai
Familyglm-5.3
Licensemit
Parameters320B / 18B
Status—
Input modalitiestext, image, video
Output modalitiestext
Architecture—
Knowledge cutoff—
Training data cutoff—
Release date—
Deprecation date—
Typechat
Reasoning tokens—
Max input—
Open weightYes
Prompt cachingSupported
Sourceofficial
Last updated

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.15
Output
$0.5
Cache write
—
Cache read
$0.03
Batch in
—
Batch out
—

Price across providers

ProviderInputOutputSince launch
OpenCode Zencheapest$0.15$0.5—
Reka AIcheapest$0.15$0.5—
Z.AI (Zhipu)cheapest$0.15$0.5—

Family Comparison: glm-5.3

ModelContextMax outPricing
GLM-5.3-FLASH1M128K$0.15$0.5
GLM-5.3-FlashX-Legal1M128K$0.37$1.25
GLM-5.3-FlashX1M128K$0.37$1.25
GLM-5.31M128K$1.4$4.4

API

GET/v1/models/zai/glm-5.3-flash

GLM-5.3-FLASH

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 · 3 entries
glm-5.3-flashupdateb2f45bfOct 29, 2026, 03:29 AM
context_window128000→1000000
capabilitiesvisionyes
modalitiesinput["text"]→["text","image","video"]
glm-5.3-flashupdate2ae168fSep 18, 2026, 06:37 AM
descriptionGLM-5.3-Flash is the first native multimodal model in the...→GLM-5.3-Flash/GLM-5.3-FlashX is the first native multimod...
glm-5.3-flashcreatee3d7dedAug 31, 2026, 04:13 AM