GLM 5.3

ZhipuReleasedAug 14, 2026

Tool use Reasoning Prompt caching Structured output

Compare GLM 5.3 Count tokens for GLM 5.3

Context

Max output

131K

Serving providers

Cheapest input

$1.40 /1M

Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis

Speed & latency

Output speed

72 t/s

tokens / second

Time to first token

1.62s

latency

Headline indices

Intelligence Index

59.5

of 100

Coding Index

74.8

of 100

Agentic Index

59.1

of 100

Individual benchmarks · click a row for effort variants

Benchmark	Best score	Effort	Cost / task
CritPt	19%	default	—
GDPval (normalized)	63%	—	—
GPQA Diamond	92%	default	—
Humanity's Last Exam	42%	default	—
Long-Context Reasoning	76%	default	—
Mlcr Overall	0.5	default	—
Omniscience	14.3	default	—
Omniscience Accuracy	0.3	default	—
Omniscience Non Hallucination	0.7	default	—
SciCode	56%	default	—
TerminalBench v2.1	84%	default	—
τ-bench Banking	50%	default	—

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Serving provider

Input /1M

Output /1M

Endpoints

ZaiCheapest

$1.40

$4.40

Endpoint	Std in	Std out	Cached in	Batch in / out	Model ID
StandardCheapest	$1.40	$4.40	$0.26	—	zai/glm-5.3

NovitaCheapest

$1.40

$4.40

OpenRouterCheapest

$1.40

$4.40

Price history

input + output $/1M since we started tracking

Input Output

Cost calculator

estimate your monthly spend on this model

Input tokens / call

Output tokens / call

Calls / month

Serving provider

$632

estimated / month

Model IDs

copy the exact identifier for your platform

zai/glm-5.3novita/zai-org/glm-5.3z-ai/glm-5.3

Frequently asked questions

GLM 5.3 pricing, context and availability

How much does GLM 5.3 cost?

GLM 5.3 costs $1.40 per 1M input tokens and $4.40 per 1M output tokens at its cheapest provider via Zai.

What is the context window of GLM 5.3?

GLM 5.3 accepts up to 1M tokens of context and can return up to 131K output tokens.

Which providers serve GLM 5.3?

GLM 5.3 is available from 3 serving providers, each with its own pricing and model ID. Zai is currently the cheapest.

What can GLM 5.3 do?

GLM 5.3 supports tool use, reasoning, prompt caching and structured output.

Other Zhipu models

compare pricing across the Zhipu lineup

GLM 5.2$0.61/1M · 10 providers GLM 4.6$0.43/1M · 7 providers GLM 4.7$0.40/1M · 6 providers GLM 4.7 Flash$0.00/1M · 5 providers GLM 4.5 Air$0.13/1M · 5 providers GLM 4.5$0.40/1M · 5 providers GLM 5$0.60/1M · 5 providers GLM 5.1$1.05/1M · 5 providers

Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI