GLM-5.3

zai-org/glm-5.3

frontier coding with emergent cyber capabilities.

cmd --model zai-org/glm-5.3

Intelligence index

not yet scored

Output speed

not yet scored

Input

$1.40 /M

Output

$4.40 /M

Cache read

$0.26 /M

Agent-loop cost

$0.60 /M in

Context window

1M tokens

Released

—

Modalities

→

vs. the lineup

GLM-5.3 beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:

Model	Intelligence	Coding	Speed	Input $/M	Output $/M	Blended $/M	Context
Muse Spark 1.2	56.8◆	72.2◆	—◆	$1.25◆	$4.25◆	$2◆	1.05M◆
GLM-5.2	52.6◆	68.8◆	124.7◆	$1.40◆	$4.40◆	$2.15◆	1M◆
GLM-5.1	41◆	55.8◆	—◆	$1.40◆	$4.40◆	$2.15◆	200K◆
GLM-5	40.6◆	—◆	—◆	$1◆	$3.20◆	$1.55◆	200K◆
GLM-5.3 ◆	—◆	—◆	—◆	$1.40◆	$4.40◆	$2.15◆	1M◆
GLM-5.2 Fast	—◆	—◆	—◆	$3◆	$10.25◆	$4.81◆	1M◆
DeepSeek V4 Pro (latest)pinned	45.3◆	59.4◆	63.3◆	$0.43◆	$0.87◆	$0.54◆	1M◆
DeepSeek V4 Flash (latest)pinned	52◆	69.1◆	115.9◆	$0.14◆	$0.28◆	$0.18◆	1M◆

Compare all 57 models →

usage calculator

How far a month of credits goes on GLM-5.3.

Input tokensfresh prompt

800

Output tokensmodel reply

180

Cache read tokensre-read context

50K

cost / request $0.015 · in $1.40 · out $4.40 · cache $0.26 per M

fresh input 8%output 5%cache reads 87%

Requests / 30 days

671

$10 credits ÷ $0.015 per request

~134 quick fixes~27 bug fixes~4 feature PRs

what real work costs

Real coding tasks priced end to end on GLM-5.3, from a quick lookup to a full-repo agent run.

One agent task

$0.15

180K in at 75% cache hit, 12K out

What you pay

$0.79 /M

all-in across every token that task touched

Sticker input

$1.40 /M

cache reads bill at $0.26 /M instead

Task	Tokens in · out	GLM-5.3	Muse Spark 1.2	Claude Haiku 4.5
Quick lookup / one-liner	8K · 1K	$0.0074	$0.0063	$0.0065
Review a 500-line PR	60K · 4K	$0.05	$0.05	$0.04
Fix a bug (agent loop)	180K · 12K	$0.15	$0.13	$0.12
Refactor a module	320K · 20K	$0.27	$0.23	$0.21
Full-repo agent run	900K · 45K	$0.66	$0.54	$0.49

frequently asked

What is GLM-5.3 best for?

frontier coding with emergent cyber capabilities.

How much does GLM-5.3 cost?

$1.40/M input and $4.40/M output, cache reads $0.26/M. In an agent loop most input is cache-read, so the effective input rate is about $0.60/M.

Which plan do I need?

Available on Go and above.

How do I switch to it?

Run cmd --model zai-org/glm-5.3, or type /model in a session and pick it. You can switch mid-session without losing context.

GLM-5.2→

powerful coding with 1M context and long-horizon tasks · $1.40/$4.40 per M

GLM-5.2 Fast→

high-throughput GLM-5.2 with 1M context · $3/$10.25 per M

All supported models→

sortable by score, speed and price