Skip to content

Listings

All listings for GLM 5.2

Every priced listing we track for this model. Back to GLM 5.2

ProviderMax Input TokensInput $/1MOutput $/1M$/input image$/requestTok/sLatency
Run by the model's maker
 Zhipu AI (Open Platform)
glm-5.2Source: Zhipu BigModel Open Platform Pricing
Data from Zhipu BigModel Open Platform Pricing
1M
CN¥8.00cache read CN¥2.00
≈ $1.1952 USD (compared by USD value)
CN¥28.00
≈ $4.1833 USD (compared by USD value)
————
Run by the model's maker
 Z.ai
policy notes
is processed in real-time to provide the Customer and End Users with the API Service and is not saved on our servers. — Z.ai privacy policy Source: Z.ai privacy policy
GLM-5.2 · fp8Sources: GenAI Prices data, LiteLLM data, Models.dev data, Z.AI Pricing
Data from Z.AI Pricing
Fields by sourceFrom GenAI Prices: offering name, context length, unitFrom LiteLLM: max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-write priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$1.40cache read $0.26$4.40————
 Microsoft Azureazure_ai/FW-GLM-5.2Source: LiteLLM data
Data from LiteLLM
1M$1.54cache read $0.15$4.84————
 Microsoft Azureazure_ai/FW-GLM-5.2-Fast · fastSource: LiteLLM data
Data from LiteLLM
1M$2.31cache read $0.231$7.26————
 GoogleRegions: globalvertex_ai/zai-org/glm-5.2-maas · maasSources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$1.40cache read $0.14$4.40————
 302aiglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Aihubmixcoding-glm-5.2-free · coding, freeSource: AIHubMix data docs
Data from AIHubMix
1M$0.00$0.00————
 Aihubmix
undercut?
Suspiciously low input price: $0.06/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
coding-glm-5.2 · codingSource: AIHubMix data docs
Data from AIHubMix
1M$0.06$0.22————
 Aihubmixglm-5.2Source: AIHubMix data docs
Data from AIHubMix
1M$1.1268cache read $0.2817$3.9438————
 Atlascloudzai-org/glm-5.2Source: AtlasCloud data
Data from AtlasCloud
1M$1.40cache read $0.26$4.40————
 Cometapiglm-5.2Sources: CometAPI data, CometAPI Pricing data
Data from CometAPI
Fields by sourceFrom CometAPI Pricing: supported input modalities, supported output modalities, currency, unit, last updated, input tokens, output tokens
Not published by the provider$1.40$4.41————
 Cortecs AIglm-5.2Sources: Cortecs EU Router data, Models.dev data
Data from Cortecs EU Router
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M
€1.167cache read €0.224
≈ $1.2807 USD (compared by USD value)
€3.77
≈ $4.1371 USD (compared by USD value)
————
 Eden AIInference by Z.aizai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Eurouterglm-5.2Source: EURouter data
Data from EURouter
1M$1.50cache read $0.375$4.50————
 Evolinkglm-5.2Sources: EvoLink data, EvoLink Pricing
Data from EvoLink
Fields by sourceFrom EvoLink Pricing: input tokens, output tokens, currency, unit, last updated
Not published by the provider$1.1765$4.1176————
 Fastrouterz-ai/glm-5.2Source: FastRouter data
Data from FastRouter
1M$0.5625cache read $0.105$1.80————
 Flowdot
undercut?
Suspiciously low output price: $0.50/1M against the official $4.1854/1M. We leave it out of the cheapest prices.
accounts/fireworks/routers/glm-5p2-fast · fastSource: FlowDot data
Data from FlowDot
1M$0.50$0.50————
 Flowdotz-ai/glm-5.2Source: FlowDot data
Data from FlowDot
1M$1.26$3.00————
 Geoddzai-org/glm-5.2Source: GeoDD
Data from GeoDD
1M$0.90$2.80————
 Hugging Face
undercut?
Suspiciously low input price: $0.007/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by Waferzai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.007$6.80————
 Hugging FaceInference by Relacezai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.31$2.40————
 Hugging FaceInference by DeepInfrazai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.5625$1.80————
 Hugging FaceInference by Coreweavezai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.62$2.42————
 Hugging FaceInference by Morphzai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.643$1.978————
 Hugging FaceInference by Digitaloceanzai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$0.70$2.20————
 Hugging FaceInference by Basetenzai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$1.40$4.40————
 Hugging Facezai-org/GLM-5.2Source: Models.dev data
Data from Models.dev
262K$1.40$4.40————
 Hugging FaceInference by Mistral AIzai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$1.40$4.40————
 Hugging FaceInference by Nebius AI Studiozai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$1.40$4.40————
 Hugging FaceInference by Novita AIzai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$1.40$4.40————
 Hugging FaceInference by Parasailzai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$1.40$4.40————
 Hugging FaceInference by Together AIzai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$1.40$4.40————
 Hugging FaceInference by Venicezai-org/GLM-5.2Source: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
1M$1.40$4.40————
 Kiloz-ai/glm-5.2Sources: Kilo AI Gateway data, Models.dev data
Data from Kilo AI Gateway
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$1.40cache read $0.14$4.40————
 Kiloz-ai/glm-5.2-fast · fastSources: Kilo AI Gateway data, Models.dev data
Data from Kilo AI Gateway
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$2.80cache read $0.56$8.80$0.00———
 Llmgatewayglm-5.2Source: LLMGateway data
Data from LLMGateway
1M$0.60cache read $0.09$2.00————
 LlmgatewayInference by Alibaba Cloudglm-5.2Source: LLMGateway data
Data from LLMGateway
Not published by the provider$1.40cache read $0.28$4.40————
 LlmgatewayInference by Nebius AI Studiozai-org/GLM-5.2Source: LLMGateway data
Data from LLMGateway
Not published by the provider$1.40$4.40————
 LlmgatewayInference by Novita AIzai-org/glm-5.2Source: LLMGateway data
Data from LLMGateway
Not published by the provider$1.40cache read $0.26$4.40————
 LlmgatewayInference by Z.aiglm-5.2Source: LLMGateway data
Data from LLMGateway
Not published by the provider$1.40cache read $0.26$4.40————
 Llmgatewayglm-5.2-fast · fastSource: LLMGateway data
Data from LLMGateway
1M$2.1256cache read $0.429$6.776————
 Meganovazai-org/GLM-5.2 · fp8Source: MegaNova data
Data from MegaNova
1M$1.00$3.00————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
undercut?
Suspiciously low input price: $0.0074/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by Wafer UsRegions: 🇺🇸 USz-ai/glm-5.2 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0074cache read $0.0063$7.14————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
undercut?
Suspiciously low input price: $0.0074/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by Wafer UsRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0074cache read $0.0063$7.14————
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
undercut?
Suspiciously low input price: $0.1985/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by BaiduRegions: 🇨🇳 CNz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1985cache read $0.0369$0.6237——59.21,389ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
undercut?
Suspiciously low input price: $0.1985/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by BaiduRegions: 🇨🇳 CNz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1985cache read $0.0369$0.6237——60.71,589ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
undercut?
Suspiciously low input price: $0.1995/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by WaferRegions: 🇺🇸 USz-ai/glm-5.2 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1995cache read $0.189$8.40——74819ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
undercut?
Suspiciously low input price: $0.1995/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by WaferRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1995cache read $0.189$8.40——1351,039ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by StreamlakeRegions: 🇨🇳 CNz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.294cache read $0.0546$0.924——51.72,183ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by StreamlakeRegions: 🇨🇳 CNz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.294cache read $0.0546$0.924——50.22,873ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by RelaceRegions: UNKz-ai/glm-5.2 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.3255cache read $0.0788$2.52——1721,143ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by RelaceRegions: UNKz-ai/glm-5.2:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.3255cache read $0.0788$2.52——1721,143ms
 NanoGPTz-ai/glm-5.2Sources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.53cache read $0.10$1.79————
 NanoGPTz-ai/glm-5.2:thinking · thinkingSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.53cache read $0.10$1.79————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by DeepInfraRegions: 🇺🇸 USz-ai/glm-5.2 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.5906cache read $0.1103$1.89——79.82,302ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by DeepInfraRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.5906cache read $0.1103$1.89——77.82,714ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by Ambientz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.63cache read $0.1575$2.10————
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by Ambientz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.63cache read $0.1575$2.10————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by Scx EuRegions: 🇪🇺 EUz-ai/glm-5.2 · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.6353cache read $0.1617$2.2292——64.55,598ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by Scx EuRegions: 🇪🇺 EUz-ai/glm-5.2:thinking · thinking · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.6353cache read $0.1617$2.2292——57.34,937ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by ScxRegions: GLBz-ai/glm-5.2 · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.6353cache read $0.1617$2.2292——59.14,578ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by ScxRegions: GLBz-ai/glm-5.2:thinking · thinking · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.6353cache read $0.1617$2.2292——76.25,266ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by CoreweaveRegions: 🇺🇸 USz-ai/glm-5.2 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.651cache read $0.147$2.541————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by CoreweaveRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.651cache read $0.147$2.541——169.7918ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by MorphRegions: 🇺🇸 USz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.6752cache read $0.2279$2.0769——130.32,377ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by MorphRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.6752cache read $0.2279$2.0769——84.62,586ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: License permits distillation — NanoGPT privacy policy
Inference by SiliconFlowRegions: 🇸🇬 SGz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.6836cache read $0.1365$2.1483——73.91,308ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: License permits distillation — NanoGPT privacy policy
Inference by SiliconFlowRegions: 🇸🇬 SGz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.6836cache read $0.1365$2.1483——73.91,308ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by EngyRegions: GLBz-ai/glm-5.2Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.714cache read $0.189$1.575————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by EngyRegions: GLBz-ai/glm-5.2:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.714cache read $0.189$1.575————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by RunwareRegions: UNKz-ai/glm-5.2Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.756cache read $0.1512$2.4098————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by RunwareRegions: UNKz-ai/glm-5.2:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.756cache read $0.1512$2.4098————
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Alibaba CloudRegions: 🇸🇬 SGz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.0143cache read $0.2029$3.1878————
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Alibaba CloudRegions: 🇸🇬 SGz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.0143cache read $0.2029$3.1878————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by Asterz-ai/glm-5.2Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.05cache read $0.21$4.20————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by Asterz-ai/glm-5.2:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$1.05cache read $0.21$4.20————
 NanoGPT
logs, may train, per NanoGPT
Data privacy: logged and may be used for training · retains prompts · may train on prompts Source: NanoGPT
policy notes
privacy: logs_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by MeganovaRegions: 🇺🇸 USz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.05cache read $0.189$3.15————
 NanoGPT
logs, may train, per NanoGPT
Data privacy: logged and may be used for training · retains prompts · may train on prompts Source: NanoGPT
policy notes
privacy: logs_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by MeganovaRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.05cache read $0.189$3.15————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by ParasailRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.155cache read $0.21$3.465————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by TensorixRegions: 🇪🇺 EUz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.155cache read $0.2888$3.465————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by TensorixRegions: 🇪🇺 EUz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.155cache read $0.2888$3.465——248.65,524ms
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
TEE/glm-5.2 · teeSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$1.25cache read $0.125$3.95————
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
TEE/glm-5.2:thinking · tee, thinkingSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$1.25cache read $0.125$3.95————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by UomiRegions: GLBz-ai/glm-5.2 · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.2737$4.0082——70.51,198ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by UomiRegions: GLBz-ai/glm-5.2:thinking · thinking · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.2737$4.0082——68.93,491ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by AtlascloudRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by BasetenRegions: 🇺🇸 USz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.147$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by BasetenRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.147$4.62————
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by Friendli AIRegions: 🇺🇸 USz-ai/glm-5.2Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62————
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by Friendli AIRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by KitaniRegions: GLBz-ai/glm-5.2Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by KitaniRegions: GLBz-ai/glm-5.2:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by Nebius AI StudioRegions: GLBz-ai/glm-5.2 · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.147$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by Nebius AI StudioRegions: GLBz-ai/glm-5.2:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.147$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by Novita AIRegions: 🇺🇸 USz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62——44.63,533ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by Novita AIRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62——56.53,236ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by OllamaRegions: UNKz-ai/glm-5.2Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by OllamaRegions: UNKz-ai/glm-5.2:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62————
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by Together AIRegions: 🇺🇸 USz-ai/glm-5.2Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62——122573ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by Together AIRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62——189.91,648ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by VeniceRegions: 🇺🇸 USz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62——84.91,760ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by VeniceRegions: 🇺🇸 USz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62——119.95,093ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Z.aiRegions: 🇸🇬 SGz-ai/glm-5.2 · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62——45.12,560ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by Z.aiRegions: 🇸🇬 SGz-ai/glm-5.2:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$1.47cache read $0.273$4.62——45.12,560ms
 Nous Portalz-ai/glm-5.2:batch · batchSource: Nous Portal Inference Gateway data
Data from Nous Portal Inference Gateway
1M$0.322cache read $0.109$0.989————
 Nous Portalz-ai/glm-5.2Source: Nous Portal Inference Gateway data
Data from Nous Portal Inference Gateway
1M$0.90cache read $0.16$2.83————
 Openroute Cnglm-5.2Source: OpenRoute CN Marketplace
Data from OpenRoute CN Marketplace
1M
CN¥8.00
≈ $1.1952 USD (compared by USD value)
CN¥28.00
≈ $4.1833 USD (compared by USD value)
————
 OpenRouter
undercut?
Suspiciously low input price: $0.007/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by Waferz-ai/glm-5.2 · us · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.007cache read $0.006$6.80——102426ms
 OpenRouter
undercut?
Suspiciously low input price: $0.189/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by Baiduz-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.189cache read $0.0351$0.594——501,183ms
 OpenRouter
undercut?
Suspiciously low input price: $0.19/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
Inference by Waferz-ai/glm-5.2 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.19cache read $0.18$8.00——107413ms
 OpenRouterInference by Streamlakez-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.28cache read $0.052$0.88——412,023ms
 OpenRouterInference by Relacez-ai/glm-5.2 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.31cache read $0.075$2.40——74942ms
 OpenRouterInference by Morphz-ai/glm-5.2:batch · batch, fp8 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.322cache read $0.109$0.989————
 OpenRouterz-ai/glm-5.2:batch · batchSource: OpenRouter data docs
Data from OpenRouter
1M$0.322cache read $0.109$0.989————
 OpenRouterInference by DeepInfraz-ai/glm-5.2 · fp4/flex · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.45cache read $0.084$1.44——671,965ms
 OpenRouterInference by DeepInfraz-ai/glm-5.2 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.5625cache read $0.105$1.80——64670.5ms
 OpenRouterInference by Ambientz-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
203K$0.60cache read $0.15$2.00——851,004ms
 OpenRouterInference by Coreweavez-ai/glm-5.2 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.62cache read $0.14$2.42——211621ms
 OpenRouterz-ai/glm-5.2Sources: GenAI Prices data, Models.dev data, OpenRouter data docs
Data from OpenRouter
Fields by sourceFrom GenAI Prices: offering nameFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.62cache read $0.14$2.42————
 OpenRouterInference by Morphz-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.643cache read $0.217$1.978——91616ms
 OpenRouterInference by SiliconFlowz-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.651cache read $0.13$2.046——721,130ms
 OpenRouterInference by Digitaloceanz-ai/glm-5.2Source: OpenRouter data docs
Data from OpenRouter
1M$0.70cache read $0.105$2.20——94.5689ms
 OpenRouterInference by Novita AIz-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.77cache read $0.143$2.42——443,015ms
 OpenRouterInference by DeepInfraz-ai/glm-5.2 · fp4/priority · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$0.8438cache read $0.1575$2.70——66908.5ms
 OpenRouterInference by Alibaba Cloudz-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$0.966cache read $0.1932$3.036——57.51,391.5ms
 OpenRouterInference by Alibaba Cloudz-ai/glm-5.2 · fp8/us-east-1 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$1.12cache read $0.224$3.52——641,431ms
 OpenRouterInference by Basetenz-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$1.40cache read $0.14$4.40——75908ms
 OpenRouterInference by Basetenz-ai/glm-5.2 · fp8/us · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$1.40cache read $0.14$4.40——881,362.5ms
 OpenRouterInference by Friendli AIz-ai/glm-5.2Source: OpenRouter data docs
Data from OpenRouter
1M$1.40cache read $0.26$4.40——160302.5ms
 OpenRouterInference by Mistral AIz-ai/glm-5.2 · zdrSource: OpenRouter data docs
Data from OpenRouter
1M$1.40cache read $0.14$4.40——115842ms
 OpenRouterInference by Nebius AI Studioz-ai/glm-5.2 · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$1.40cache read $0.14$4.40——89.5587ms
 OpenRouterInference by Parasailz-ai/glm-5.2 · fp4Source: OpenRouter data docs
Data from OpenRouter
262K$1.40cache read $0.26$4.40——147784ms
 OpenRouterInference by Together AIz-ai/glm-5.2Source: OpenRouter data docs
Data from OpenRouter
1M$1.40cache read $0.26$4.40——166190ms
 OpenRouterInference by Venicez-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$1.40cache read $0.26$4.40——901,455.5ms
 OpenRouterInference by Z.aiz-ai/glm-5.2 · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$1.40cache read $0.26$4.40——382,100ms
 OpenRouterInference by Mistral AIz-ai/glm-5.2 · euSource: OpenRouter data docs
Data from OpenRouter
1M$1.54cache read $0.154$4.84——188787ms
 OpenRouterInference by Basetenz-ai/glm-5.2 · fast · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$2.10cache read $0.21$6.60——194.5459.5ms
 OpenRouterInference by Basetenz-ai/glm-5.2 · us/fast · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$2.10cache read $0.21$6.60——184383ms
 OpenRouterInference by Baiduz-ai/glm-5.2 · fast · fp4Source: OpenRouter data docs
Data from OpenRouter
1M$2.25cache read $0.56$7.88——92733.5ms
 OpenRouterInference by Alibaba Cloudz-ai/glm-5.2 · fast · fp8Source: OpenRouter data docs
Data from OpenRouter
1M$2.31cache read $0.462$7.26——149.5542.5ms
 Redpill
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
z-ai/glm-5.2Source: RedPill data
Data from RedPill
1M$1.26$3.00————
 RequestyInference by Doubleworddoubleword/glm-5.2:flex · flexSource: Requesty data
Data from Requesty
1M$1.05$3.30————
 RequestyInference by Inceptroninceptron/glm-5.2Source: Requesty data
Data from Requesty
1M$1.20cache read $0.26$4.20————
 RequestyInference by Sferencesference/glm-5.2Source: Requesty data
Data from Requesty
1M$1.20cache read $0.26$4.20————
 RequestyInference by Doubleworddoubleword/glm-5.2Source: Requesty data
Data from Requesty
1M$1.40$4.40————
 RequestyInference by Nebius AI Studionebius/glm-5.2Source: Requesty data
Data from Requesty
1M$1.40$4.40————
 RequestyInference by Z.aizai/glm-5.2Source: Requesty data
Data from Requesty
1M$1.40cache read $0.26$4.40————
 RequestyInference by Tensorxtensorx/glm-5.2Source: Requesty data
Data from Requesty
1M$1.50cache read $0.38$4.50————
 Tokenmixglm-5.2Sources: TokenMix data, TokenMix Pricing
Data from TokenMix
Fields by sourceFrom TokenMix Pricing: currency, last updated, unit, input tokens, output tokens
Not published by the provider$1.1176$3.9118————
 Tokensmindglm-5.2Source: TokensMind
Data from TokensMind
Not published by the provider$1.14$4.00————
 Vercel
policy notes
AI Gateway uses zero data retention by default — Vercel AI Gateway security & compliance documentation It permanently deletes your prompts and responses after requests complete. — Vercel AI Gateway security & compliance documentation requests only route to providers with verified ZDR agreements — Vercel AI Gateway security & compliance documentation The provider allowlist lets team owners restrict which AI providers can serve requests through AI Gateway — Vercel AI Gateway security & compliance documentation Vercel may store, process and transmit your information outside of your country of residence, which may have different data protection laws and may not offer the same level of protection or guarantees as in your country or the country where you initially provided the information. — Vercel privacy policy Sources: Vercel AI Gateway security & compliance documentation, Vercel privacy policy
zai/glm-5.2Sources: Models.dev data, Vercel AI Gateway data
Data from Vercel AI Gateway
Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$1.40cache read $0.14$4.40————
 Vercel
policy notes
AI Gateway uses zero data retention by default — Vercel AI Gateway security & compliance documentation It permanently deletes your prompts and responses after requests complete. — Vercel AI Gateway security & compliance documentation requests only route to providers with verified ZDR agreements — Vercel AI Gateway security & compliance documentation The provider allowlist lets team owners restrict which AI providers can serve requests through AI Gateway — Vercel AI Gateway security & compliance documentation Vercel may store, process and transmit your information outside of your country of residence, which may have different data protection laws and may not offer the same level of protection or guarantees as in your country or the country where you initially provided the information. — Vercel privacy policy Sources: Vercel AI Gateway security & compliance documentation, Vercel privacy policy
zai/glm-5.2-fast · fastSources: Models.dev data, Vercel AI Gateway data
Data from Vercel AI Gateway
Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$2.80cache read $0.56$8.80————
 Wavespeedz-ai/glm-5.2Source: WaveSpeed AI data
Data from WaveSpeed AI
1M$1.40cache read $0.26$4.40————
 Zenmuxz-ai/glm-5.2Sources: Models.dev data, ZenMux data
Data from ZenMux
Fields by sourceFrom Models.dev: max completion tokens, supports function calling, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$1.40cache read $0.26$4.40—$0.01——
 Abacuszai-org/GLM-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Aboveglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.54cache read $0.154$4.84————
 Aboveglm-5.2-fast · fastSource: Models.dev data
Data from Models.dev
1M$2.31cache read $0.231$7.26————
 Adaptionglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Aimlapizhipu/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Alibaba CloudRegions: 🇯🇵🇸🇬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1glm-5.2 · fp8Sources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Alibaba Cloud Qwen, LiteLLM data, Models.dev data
Data from Alibaba Cloud Model Studio (DashScope) Multi-Region API
Fields by sourceFrom Alibaba Cloud Qwen: currency, last updated, input tokens, output tokens, unitFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-read priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input, cache-write price
1M$1.40cache read $0.28$4.40————
 Alibaba Cloud (China)glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.10cache read $0.275$3.851————
 Ambientz-ai/glm-5.2 · fp8Sources: Ambient data, Models.dev data
Data from Ambient
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, cache-write price
203K$0.60cache read $0.15$2.00————
 Ambientzai-org/GLM-5.2-FP8 · fp8Source: Models.dev data
Data from Models.dev
203K$1.20cache read $0.26$4.20————
 Arceezai-org/glm-5.2Source: Models.dev data
Data from Models.dev
262K$1.40cache read $0.26$4.40————
 Avianz-ai/glm-5.2Source: Avian.io Models data
Data from Avian.io Models
1M$0.495cache read $0.124$1.733————
 Baiduglm-5.2 · fp8Source: Baidu Qianfan
Data from Baidu Qianfan
Not published by the provider
CN¥8.00cache read CN¥2.00
≈ $1.1952 USD (compared by USD value)
CN¥28.00
≈ $4.1833 USD (compared by USD value)
————
 Baiduglm-5.2-fast · fast · fp4Source: Baidu Qianfan
Data from Baidu Qianfan
Not published by the provider
CN¥16.00cache read CN¥4.00
≈ $2.3904 USD (compared by USD value)
CN¥56.00
≈ $8.3665 USD (compared by USD value)
————
 Basetenzai-org/GLM-5.2 · fp8Sources: Baseten data, LiteLLM data, Models.dev data
Data from Baseten
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports tool choice, supports response schema, supports prompt caching, supports vision, max input tokens, max output tokens, cache-read priceFrom Models.dev: supports system messages, supports image input
1M$1.40cache read $0.14$4.40————
 Basetenzai-org/GLM-5.2-Fast · fast · fp8Sources: Baseten data, LiteLLM data, Models.dev data
Data from Baseten
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports tool choice, supports response schema, supports prompt caching, supports vision, max input tokens, max output tokens, cache-read priceFrom Models.dev: supports system messages, supports image input
1M$2.10cache read $0.21$6.60————
 Berget AIzai-org/GLM-5.2Source: Models.dev data
Data from Models.dev
524K$1.54$4.84————
 Boundlessglm-5.2Source: Models.dev data
Data from Models.dev
1M$0.34cache read $0.17$2.30————
 BytePlus
policy notes
service may store your Customer Data for content safety purposes; input and output triggered by the filter are retained for 180 days in *Malaysia — BytePlus ModelArk data-processing documentation has a strict internal account and data rights management policy and cannot access Customer Data unless authorized by the customer — BytePlus ModelArk data-processing documentation Source: BytePlus ModelArk data-processing documentation
glm-5-2-260617 · 260617Sources: BytePlus ModelArk Pricing, Models.dev data
Data from BytePlus ModelArk Pricing
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, cache-read price
1M$1.40cache read $0.26$4.40————
 Chutes
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
zai-org/GLM-5.2-TEE · tee · fp4Sources: Chutes data, Models.dev data
Data from Chutes
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$1.25cache read $0.125$3.95————
 Chuteszai-org/GLM-5.2-Fast · fastSources: Chutes data, Models.dev data
Data from Chutes
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$2.45cache read $0.49$7.70————
 Cline Passcline-pass/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Cloudflare Workers AIcloudflare/@cf/zai-org/glm-5.2Sources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
262K$1.40cache read $0.26$4.40————
 Commandcodezai-org/GLM-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Commandcodezai-org/GLM-5.2-Fast · fastSource: Models.dev data
Data from Models.dev
1M$3.00cache read $0.50$10.25————
 Core42glm-5.2Source: Core42 Compass Model Pricing
Data from Core42 Compass Model Pricing
Not published by the provider$1.54$4.84————
 Crossmodelz-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.20cache read $0.30$4.40cache write $1.20————
 Crusoezai/GLM-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Databricksdatabricks/databricks-glm-5-2Sources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$1.40cache read $0.26$4.40cache write $1.40————
 DeepInfrazai-org/GLM-5.2 · fp4Sources: DeepInfra data, LiteLLM data, Models.dev data
Data from DeepInfra
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input, cache-write price
1M$0.75cache read $0.14$2.40cache write $0.9375————
 Digitaloceanglm-5.2Source: Models.dev data
Data from Models.dev
262K$1.40cache read $0.21$4.40————
 Dinferenceglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.25$3.89————
 Doublewordzai-org/GLM-5.2-FP8 · fp8Source: Models.dev data
Data from Models.dev
1M$0.93cache read $0.186$3.00cache write $1.1625————
 Empiriolabsglm-5-2:variant1 · variant1Source: EmpirioLabs data
Data from EmpirioLabs
1M$1.10cache read $0.275$3.851————
 Empiriolabsglm-5-2Sources: EmpirioLabs data, LiteLLM data, Models.dev data
Data from EmpirioLabs
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports response schema, max input tokens, max output tokensFrom Models.dev: supports vision
1M$1.40$4.40————
 Empiriolabsglm-5-2:variant2 · variant2Source: EmpirioLabs data
Data from EmpirioLabs
1M$1.40$4.40————
 Engyglm-5.2Source: Models.dev data
Data from Models.dev
262K$0.68cache read $0.18$1.50————
 Evroczai-org/GLM-5.2Source: Models.dev data
Data from Models.dev
524K$1.4375$5.75————
 Fireworks AIglm-5p2Sources: GenAI Prices data, LiteLLM data
Data from GenAI Prices
Fields by sourceFrom LiteLLM: max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, supports reasoning, max input tokens, max output tokens
1M$1.40cache read $0.14$4.40————
 Fireworks AIaccounts/fireworks/routers/glm-5p2-fast · fastSources: Fireworks AI data, LiteLLM data
Data from Fireworks AI
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports function calling, supports tool choice, supports response schema, supports reasoning, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read price
1M$2.10cache read $0.21$6.60————
 Fireworks AIRegions: 🇺🇸 usfireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us · fastSource: LiteLLM data
Data from LiteLLM
1M$2.10cache read $0.21$6.60————
 FlexaiRegions: 🇪🇺 euGLM-5.2Sources: flex.ai API data, flex.ai Pricing
Data from flex.ai API
Fields by sourceFrom flex.ai Pricing: cache-read price
1M$0.60cache read $0.09$2.00————
 Friendli AIzai-org/GLM-5.2Sources: FriendliAI data, Models.dev data
Data from FriendliAI
Fields by sourceFrom Models.dev: context length, max completion tokens, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$1.40cache read $0.26$4.40————
 Gmicloudzai-org/GLM-5.2-FP8 · fp8Sources: GMI Cloud data, LiteLLM data, Models.dev data
Data from GMI Cloud
Fields by sourceFrom LiteLLM: offering name, max input tokens, supported input modalities, supported output modalities, max input tokens, currency, last updated, input tokens, output tokens, cache-read priceFrom Models.dev: max completion tokens, supports function calling, supports reasoning, supports system messages, supports vision, max output tokens, supports image input
1M$1.40cache read $0.26$4.40————
 Greenptglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.7383cache read $0.4486$5.1589————
 Hpc AIzai-org/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Huawei Maasglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.1994$4.1979————
 Impossiblfireworks/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.14$4.40————
 Ionetzai-org/GLM-5.2Source: IO Intelligence (io.net) data
Data from IO Intelligence (io.net)
262K$1.2614cache read $0.6307$5.32——0.02337.125ms
 Iteracomputez-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$0.53cache read $0.12$1.72————
 JalapenoGLM-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Kelnzai-org/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.28$4.40————
 Kenariglm-5-2Source: Models.dev data
Data from Models.dev
1M$0.2857cache read $0.0531$3.43————
 Llmgateway Providersalibaba/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.28$4.40————
 Llmgateway Providersscx-ai-gp/glm-5.2-fast · fastSource: Models.dev data
Data from Models.dev
1M$2.1256cache read $0.429$6.776————
 Merge Gatewayzai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.05cache read $0.195$3.30————
 Mistral AImistral/glm-5-2Sources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$1.40cache read $0.14$4.40————
 MorphRegions: 🇺🇸 USmorph-glm52-744b · fp8Source: Morph data
Data from Morph
1M$0.643cache read $0.217$1.978————
 Nebius AI Studionebius/zai-org/GLM-5.2 · fp4Sources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$1.40cache read $0.14$4.40————
 Neonglm-5-2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Netmindzai-org/GLM-5.2Source: NetMind.AI
Data from NetMind.AI
1M$1.40cache read $0.26$4.40————
 Novita AIzai-org/glm-5.2 · fp8Sources: LiteLLM data, Models.dev data, Novita AI data
Data from Novita AI
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports function calling, supports tool choice, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-read priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$1.40cache read $0.26$4.40————
 Ofoxz-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Ollamaglm-5.2Source: Models.dev data
Data from Models.dev
976K$1.40cache read $0.26$4.40————
 Opencode Goopencode_go/glm-5.2Sources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$1.40cache read $0.26$4.40————
 Opperglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.6271$5.811————
 Orcarouterz-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Perplexityperplexity/perplexity/glm-5.2Source: LiteLLM data
Data from LiteLLM
Not published by the provider$1.40cache read $0.14$4.40————
 Phala
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
z-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.26cache read $0.22$3.00————
 Pioneerzai-org/GLM-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40cache write $1.40————
 Ppiozai-org/glm-5.2Source: PPIO data
Data from PPIO
1M
CN¥8.00cache read CN¥2.00
≈ $1.1952 USD (compared by USD value)
CN¥28.00
≈ $4.1833 USD (compared by USD value)
————
 Primez-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.54$4.84————
 Qiniuz-ai/glm-5.2Sources: Qiniu AI data, Qiniu AI Model Plaza Pricing
Data from Qiniu AI
Fields by sourceFrom Qiniu AI Model Plaza Pricing: context length, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports structured output, rate limits, currency, unit, last updated, input tokens, output tokens, cache-read price
1M
CN¥8.00cache read CN¥2.00
≈ $1.1952 USD (compared by USD value)
CN¥28.00
≈ $4.1833 USD (compared by USD value)
————
 Regologlm5.2Sources: Models.dev data, Regolo data
Data from Regolo
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
96K$2.30$6.90————
 Routing Runglm-5.2Source: Models.dev data
Data from Models.dev
200K$0.80$2.40————
 Routing Runglm-5.2-nitro · nitroSource: Models.dev data
Data from Models.dev
200K$0.80$2.40————
 Scx AIscx-ai/GLM-5.2Sources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$0.61cache read $0.22$1.98————
 Scx AIGLM-5.2-Fast · fastSource: Models.dev data
Data from Models.dev
1M$1.99cache read $0.40$6.16————
 Sferencezai-org/GLM-5.2Source: sference data
Data from sference
1M$1.20cache read $0.26$4.20————
 SiliconFlowzai-org/GLM-5.2 · fp8Sources: Models.dev data, SiliconFlow data
Data from SiliconFlow
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, input tokens, output tokens, cache-read price, cache-write price, currency, currency basis, last updated
1M$1.302cache read $0.26$4.092————
 Siliconflow Cnzai-org/GLM-5.2Source: Models.dev data
Data from Models.dev
1M$1.1956cache read $0.2989$4.1845————
 Standardcomputez-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$0.5625cache read $0.105$1.80————
 Streamlakeglm-5-2 · fp8Sources: LiteLLM data, StreamLake Pricing
Data from StreamLake Pricing
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-read price
1M$1.40cache read $0.26$4.40————
 Tencenttencent/glm-5.2Source: LiteLLM data
Data from LiteLLM
1M$1.40cache read $0.26$4.40————
 Tensorixz-ai/glm-5.2 · fp8Sources: Tensorix data, Tensorix Pricing
Data from Tensorix
Fields by sourceFrom Tensorix Pricing: input tokens, output tokens, currency, unit, last updated
Not published by the provider$1.50$4.50————
 Tensorxz-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.50cache read $0.375$4.50————
 Together AIzai-org/GLM-5.2Sources: LiteLLM data, Models.dev data, Together AI data
Data from Together AI
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports function calling, supports parallel function calling, supports tool choice, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-read priceFrom Models.dev: max completion tokens, supports system messages, supports vision, supports image input
1M$1.40cache read $0.26$4.40————
 Tokengoz-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$1.40cache read $0.26$4.40————
 Tokenifyz-ai/glm-5.2Source: Models.dev data
Data from Models.dev
1M$0.70cache read $0.26$2.20————
 Unorouterglm-5.2:free · freeSource: Models.dev data
Data from Models.dev
1M$0.00$0.00————
 Unorouterglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.6001$5.0288————
 Venice
private, per Venice.ai
Data privacy: private Source: Venice.ai
policy notes
privacy classification: private — Venice privacy documentation
zai-org-glm-5-2 · fp8Source: Venice.ai data
Data from Venice.ai
1M$1.40cache read $0.26$4.40————
 Venice
private, per Venice.ai
Data privacy: private Source: Venice.ai
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
policy notes
privacy classification: private — Venice privacy documentation
e2ee-glm-5-2-p · e2eeSource: Venice.ai data
Data from Venice.ai
524K$1.75cache read $0.30$5.75————
 Vivgridglm-5.2Source: Models.dev data
Data from Models.dev
1M$1.20cache read $0.30$4.20————
 Volcano Engineglm-5-2-260617 · 260617Source: Models.dev data
Data from Models.dev
1M$1.1875cache read $0.2969$4.1562————
 Vultrglm-5.2Sources: Models.dev data, Vultr Serverless Inference data
Data from Vultr Serverless Inference
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, input tokens, output tokens, currency, currency basis, last updated
1M$0.75$3.00————
 Wafer
undercut?
Suspiciously low input price: $0.19/1M against the official $1.1958/1M. We leave it out of the cheapest prices.
GLM-5.2 · fp4Sources: Models.dev data, Wafer data
Data from Wafer
Fields by sourceFrom Models.dev: max completion tokens, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
1M$0.19cache read $0.18$4.40————
 Weights & Biaseszai-org/GLM-5.2Sources: LiteLLM data, Models.dev data, Weights & Biases Inference data
Data from Weights & Biases Inference
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports prompt caching, supports reasoning, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read priceFrom Models.dev: max completion tokens, supports function calling, supports system messages, supports vision, supports image input
262K$0.62cache read $0.14$2.42————
 WattGLM-5.2Source: Models.dev data
Data from Models.dev
1M$1.40$4.40————

18 listings without a price are hidden.

Select any dotted value, label or icon to see where it comes from and how it is measured. How this data works