Z.ai: GLM 5.3 Flash

Name: Z.ai: GLM 5.3 Flash
Author: OpenRouter

deprecated

GLM-5.3-Flash is a native multimodal model from Z.ai.

Context

1.0M

Max output

944K

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

Model IDz-ai/glm-5.3-flash

ProviderOpenRouter

Creatorz-ai

Familyglm-5.3

License—

Parameters—

Statusdeprecated

Input modalitiestext, image, video

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date2026-08-26

Deprecation date2098-12-31

Typechat

Reasoning tokens—

Max input—

Open weight—

Sourceofficial

Last updated2026-09-30

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.15

↑233%$0.05

Output

$0.5

↑257%$0.14

Cache write

—

Cache read

$0.03

↑200%$0.01

Batch in

—

Batch out

—

Price history · $/1M input

$0.075

$0.15

$0.1

$0.09

$0.15

$0.045

$0.04

$0.045

$0.15

Aug 31Sep 11Sep 16Sep 17Sep 22Sep 25Sep 26Sep 27Sep 28

Date	Input	Output	Cache read	Change
Aug 31, 2026	$0.075	$0.25	$0.015	—
Sep 11, 202617bcfbf	$0.15	$0.5	$0.03	↑100%
Sep 16, 202640decde	$0.1	$0.333	$0.02	↓33%
Sep 17, 2026a6f5da0	$0.09	$0.3	$0.018	↓10%
Sep 22, 2026f13f134	$0.15	$0.5	$0.05	↑67%
Sep 25, 202699b2555	$0.045	$0.6	$0.029	↓70%
Sep 26, 20269cb03f8	$0.04	$0.5	$0.015	↓11%
Sep 27, 20266ba56d7	$0.045	$0.14	$0.01	↑12%
Sep 28, 2026f41f4c4	$0.15	$0.5	$0.03	↑233%

Input is ↑100% since Aug 31, 2026, from $0.075 to $0.15 per 1M tokens.

Family Comparison: glm-5.3

Model	Caps	Perf	Speed	Context	Max out	Pricing
Z.ai: GLM 5.3	RVTS	—	—	1.0M	944K	$0.04$4.8
Z.ai: GLM 5.3 Flash (batch)	RVTS	—	—	1.0M	131K	$0.06$0.2
Z.ai: GLM 5.3 Flash	RVTS	—	—	1.0M	944K	$0.15$0.5
Z.ai: GLM 5.3 FlashX	RVTS	—	—	1.0M	131K	$0.37$1.25
Z.ai: GLM 5.3 (batch)	RVTS	—	—	1.0M	131K	$0.45$2
Z.ai: GLM 5.3 Prime	RVTS	—	—	1M	131K	$2.8$8.8

API

GET/v1/models/openrouter/z-ai/glm-5.3-flash