zai-orgListed Jun 16, 2026

GLM-5.2

GLM-5.2 is Z-AI's latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context.

Compare

Context window1M

Max output943.7K

Provider endpoints44

Benchmark results0

Tool calling Structured output Reasoning Prompt caching Open weights

Measured performance

Benchmark results

All leaderboards ↗

—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

44 quotes

Your token mix

USD · listed token rates

Input million tokensOutput million tokens

novita · via Hugging Face

$2.50

together · via Hugging Face

$2.50

scaleway · via Hugging Face

$3.6195

baseten · via Hugging Face

$2.50

deepinfra · via Hugging Face

$1.35

DeepInfra

$1.35

ExperientialStandard list rate

$2.75

Wafer · via OpenRouterwafer/us · quantization=fp4

$1.7841

Relace · via OpenRouterrelace

$1.575

Morph · via OpenRoutermorph/fp8 · quantization=fp8

$1.579

Baidu · via OpenRouterbaidu/fp8 · quantization=fp8

$0.3375

Cloudflare · via OpenRoutercloudflare

$2.19

Wafer · via OpenRouterwafer · quantization=fp4

$2.69

DeepInfra · via OpenRouterdeepinfra/fp4/flex · tier=flex · quantization=fp4

$0.81

StreamLake · via OpenRouterstreamlake/fp8 · quantization=fp8

$0.992

DeepInfra · via OpenRouterdeepinfra/fp4 · quantization=fp4

$1.0125

CoreWeave · via OpenRoutercoreweave/fp4 · quantization=fp4

$1.225

Novita · via OpenRouternovita/fp8 · quantization=fp8

$1.16

Inceptron · via OpenRouterinceptron/fp4 · quantization=fp4

$0.9499

DigitalOcean · via OpenRouterdigitalocean

$1.25

SiliconFlow · via OpenRoutersiliconflow/fp8 · quantization=fp8

$1.25

AtlasCloud · via OpenRouteratlas-cloud/fp8 · quantization=fp8

$1.675

Alibaba · via OpenRouteralibaba/fp8/us-east-1 · quantization=fp8

$2.00

Phala · via OpenRouterphala/fp8 · quantization=fp8

$2.01

Nebius · via OpenRouternebius/fp4 · quantization=fp4

$2.50

Mistral · via OpenRoutermistral/zdr · quantization=nvfp4

$2.50

BaseTen · via OpenRouterbaseten/fp8/us · quantization=fp8

$2.50

Together · via OpenRoutertogether

$2.50

BaseTen · via OpenRouterbaseten/fp8 · quantization=fp8

$2.50

Venice · via OpenRoutervenice/fp8 · quantization=fp8

$2.50

GMICloud · via OpenRoutergmicloud/fp8 · quantization=fp8

$2.50

Parasail · via OpenRouterparasail/fp4 · quantization=fp4

$2.50

Friendli · via OpenRouterfriendli

$2.50

Z.AI · via OpenRouterz-ai/fp8 · quantization=fp8

$2.50

Mistral · via OpenRoutermistral/eu

$2.75

Baidu · via OpenRouterbaidu/fast · tier=priority · quantization=fp4

$4.22

Alibaba · via OpenRouteralibaba/fast · tier=priority · quantization=fp8

$4.125

Decart · via OpenRouterdecart/fast · tier=priority · quantization=fp4

$4.75

OpenRouter

Catalog quote

Input: $0.62
Output: $2.42
Cached input: $0.14

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2

novita

via Hugging Face

Input: $1.40
Output: $4.40

USD / 1M tokens

1M contextPrice source ↗Checked Oct 17, 2026

Endpoint ID

zai-org/GLM-5.2

together

via Hugging Face

Input: $1.40
Output: $4.40

USD / 1M tokens

1M contextPrice source ↗Checked Oct 17, 2026

Endpoint ID

zai-org/GLM-5.2

featherless-ai

via Hugging Face

Input: —
Output: —

USD / 1M tokens

Price source ↗Checked Oct 17, 2026

Endpoint ID

zai-org/GLM-5.2

zai-org

via Hugging Face

Input: —
Output: —

USD / 1M tokens

Price source ↗Checked Oct 17, 2026

Endpoint ID

zai-org/GLM-5.2

scaleway

via Hugging Face

Input: $2.052
Output: $6.27

USD / 1M tokens

Price source ↗Checked Oct 17, 2026

Endpoint ID

zai-org/GLM-5.2

baseten

via Hugging Face

Input: $1.40
Output: $4.40

USD / 1M tokens

1M contextPrice source ↗Checked Oct 17, 2026

Endpoint ID

zai-org/GLM-5.2

deepinfra

via Hugging Face

Input: $0.75
Output: $2.40

USD / 1M tokens

1M contextPrice source ↗Checked Oct 17, 2026

Endpoint ID

zai-org/GLM-5.2

DeepInfra

Input: $0.75
Output: $2.40

USD / 1M tokens

1M contextPrice source ↗Checked Oct 17, 2026

Endpoint ID

zai-org/GLM-5.2

Experiential

Standard list rate

Input: $1.54
Output: $4.84
Cached input: $0.15

USD / 1M tokens

Catalog list rate. Plan allowances and temporary discounts are separate.

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

glm-5.2

Wafer

via OpenRouter

wafer/us · quantization=fp4

Input: $0.0341
Output: $7.00
Cached input: $0.033

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::wafer/us

Relace

via OpenRouter

relace

Input: $0.075
Output: $6.00
Cached input: $0.075

USD / 1M tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::relace

Morph

via OpenRouter

morph/fp8 · quantization=fp8

Input: $0.079
Output: $6.00
Cached input: $0.079

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::morph/fp8

Baidu

via OpenRouter

baidu/fp8 · quantization=fp8

Input: $0.189
Output: $0.594
Cached input: $0.0351

USD / 1M tokens

Source discount 86.5%; rates as published

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::baidu/fp8

Cloudflare

via OpenRouter

cloudflare

Input: $0.19
Output: $8.00
Cached input: $0.19

USD / 1M tokens

262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::cloudflare

Wafer

via OpenRouter

wafer · quantization=fp4

Input: $0.19
Output: $10.00
Cached input: $0.18

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::wafer

DeepInfra

via OpenRouter

deepinfra/fp4/flex · tier=flex · quantization=fp4

Input: $0.45
Output: $1.44
Cached input: $0.084

USD / 1M tokens

Source discount 25%; rates as published

1M context163.8K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::deepinfra/fp4/flex

StreamLake

via OpenRouter

streamlake/fp8 · quantization=fp8

Input: $0.5555
Output: $1.7459
Cached input: $0.1032

USD / 1M tokens

Source discount 60.32%; rates as published

1M context128K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::streamlake/fp8

DeepInfra

via OpenRouter

deepinfra/fp4 · quantization=fp4

Input: $0.5625
Output: $1.80
Cached input: $0.105

USD / 1M tokens

Source discount 25%; rates as published

1M context163.8K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::deepinfra/fp4

CoreWeave

via OpenRouter

coreweave/fp4 · quantization=fp4

Input: $0.62
Output: $2.42
Cached input: $0.14

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::coreweave/fp4

Novita

via OpenRouter

novita/fp8 · quantization=fp8

Input: $0.6496
Output: $2.0416
Cached input: $0.1206

USD / 1M tokens

Source discount 53.6%; rates as published

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::novita/fp8

Inceptron

via OpenRouter

inceptron/fp4 · quantization=fp4

Input: $0.69
Output: $1.0395
Cached input: $0.14

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::inceptron/fp4

DigitalOcean

via OpenRouter

digitalocean

Input: $0.70
Output: $2.20
Cached input: $0.105

USD / 1M tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::digitalocean

SiliconFlow

via OpenRouter

siliconflow/fp8 · quantization=fp8

Input: $0.70
Output: $2.20
Cached input: $0.13

USD / 1M tokens

Source discount 50%; rates as published

1M context262.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::siliconflow/fp8

AtlasCloud

via OpenRouter

atlas-cloud/fp8 · quantization=fp8

Input: $0.938
Output: $2.948
Cached input: $0.1742

USD / 1M tokens

Source discount 33%; rates as published

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::atlas-cloud/fp8

Alibaba

via OpenRouter

alibaba/fp8 · quantization=fp8

Provider degraded

Input: $0.966
Output: $3.036
Cached input: $0.1932

USD / 1M tokens

Max prompt 1048576 tokens · Endpoint degraded (status -2)

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::alibaba/fp8

Alibaba

via OpenRouter

alibaba/fp8/us-east-1 · quantization=fp8

Input: $1.12
Output: $3.52
Cached input: $0.224

USD / 1M tokens

Max prompt 1048576 tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::alibaba/fp8/us-east-1

Phala

via OpenRouter

phala/fp8 · quantization=fp8

Input: $1.26
Output: $3.00
Cached input: $0.22

USD / 1M tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::phala/fp8

Nebius

via OpenRouter

nebius/fp4 · quantization=fp4

Input: $1.40
Output: $4.40

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::nebius/fp4

Mistral

via OpenRouter

mistral/zdr · quantization=nvfp4

Input: $1.40
Output: $4.40
Cached input: $0.14

USD / 1M tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::mistral/zdr

BaseTen

via OpenRouter

baseten/fp8/us · quantization=fp8

Input: $1.40
Output: $4.40
Cached input: $0.14

USD / 1M tokens

1M context262.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::baseten/fp8/us

Together

via OpenRouter

together

Input: $1.40
Output: $4.40
Cached input: $0.26

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::together

BaseTen

via OpenRouter

baseten/fp8 · quantization=fp8

Input: $1.40
Output: $4.40
Cached input: $0.14

USD / 1M tokens

1M context262.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::baseten/fp8

Venice

via OpenRouter

venice/fp8 · quantization=fp8

Input: $1.40
Output: $4.40
Cached input: $0.26

USD / 1M tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::venice/fp8

GMICloud

via OpenRouter

gmicloud/fp8 · quantization=fp8

Input: $1.40
Output: $4.40
Cached input: $0.26

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::gmicloud/fp8

Parasail

via OpenRouter

parasail/fp4 · quantization=fp4

Input: $1.40
Output: $4.40
Cached input: $0.26

USD / 1M tokens

262.1K context235.9K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::parasail/fp4

Friendli

via OpenRouter

friendli

Input: $1.40
Output: $4.40
Cached input: $0.26

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::friendli

Z.AI

via OpenRouter

z-ai/fp8 · quantization=fp8

Input: $1.40
Output: $4.40
Cached input: $0.26

USD / 1M tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::z-ai/fp8

Mistral

via OpenRouter

mistral/eu

Input: $1.54
Output: $4.84
Cached input: $0.154

USD / 1M tokens

1M context128K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::mistral/eu

BaseTen

via OpenRouter

baseten/us/fast · tier=priority · quantization=fp8

Provider degraded

Input: $2.10
Output: $6.60
Cached input: $0.21

USD / 1M tokens

Endpoint degraded (status -2)

1M context262.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::baseten/us/fast

BaseTen

via OpenRouter

baseten/fast · tier=priority · quantization=fp8

Provider degraded

Input: $2.10
Output: $6.60
Cached input: $0.21

USD / 1M tokens

Endpoint degraded (status -2)

1M context262.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::baseten/fast

Baidu

via OpenRouter

baidu/fast · tier=priority · quantization=fp4

Input: $2.25
Output: $7.88
Cached input: $0.56

USD / 1M tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::baidu/fast

Alibaba

via OpenRouter

alibaba/fast · tier=priority · quantization=fp8

Input: $2.31
Output: $7.26
Cached input: $0.462

USD / 1M tokens

Max prompt 1048576 tokens

1M context131.1K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::alibaba/fast

Decart

via OpenRouter

decart/fast · tier=priority · quantization=fp4

Input: $2.50
Output: $9.00
Cached input: $0.54

USD / 1M tokens

1M context943.7K max outputPrice source ↗Checked Oct 17, 2026

Endpoint ID

z-ai/glm-5.2::decart/fast

Model specifications

Developer: zai-org
Modality: Language
Context: 1,048,576 tokens
Maximum output: 943,718 tokens
Weights: Open weights
Provider listed: Jun 16, 2026
First discovered: Oct 16, 2026

Exact identities

openrouterz-ai/glm-5.2
huggingfacezai-org/GLM-5.2
deepinfrazai-org/GLM-5.2
experientialglm-5.2

Sources

OpenRouter ↗Hugging Face ↗DeepInfra ↗Experiential ↗

Updated Oct 17, 2026

More from zai-org

View all ↗

zai-orgReleased Aug 26

GLM-5.3-Flash

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context…

1M contextImage inputVideo input

AA IntelligenceEffort: max41.81 LiveBenchEffort: max · single run · equal mean of 7 suites70.61%

$0.06in$1.60out/ 1M tokens · USDReka · via OpenRouter · 46 endpointsreka

+Compare

zai-orgListed Aug 25