About GLM-5.2

GLM 5.2 est un modèle de raisonnement à grande échelle développé par Z.ai. Il prend en charge les entrées et sorties textuelles avec une fenêtre de contexte de 1 million de tokens, et est adapté aux workflows d'agents à long terme, à l'ingénierie logicielle au niveau des projets, etc.

GLM-5.2 est un modèle conversationnel développé par Z.ai, disponible sur Eden AI via 15 endpoints chez 14 fournisseurs, à partir de 0,75 $ par million de tokens en entrée et 2,4 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

15 endpoints from 14 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint

Region

Context

Input / 1M

Output / 1M

Cached / 1M

Supports

DeepInfra (États-Unis)Official−%deepinfra/zai-org/GLM-5.2

États-Unis

1.05M

$0.75$0.75

$2.4

$0.14

ReasoningToolsJSONCacheVisionWeb

QwenOfficial−35%qwen/glm-5.2

Monde

1M

$1.4$0.91

$2.86

$0.182

ReasoningToolsJSONCacheVisionWeb

FlexAIOfficial−%flexai/GLM-5.2

Monde

1.05M

$0.966$0.966

$3.036

$0.1449

ReasoningToolsJSONCacheVisionWeb

Multiverse ComputingOfficial−%compactifai/glm-5-2

Monde

$1.1$1.1

$3.5

$0.22

ReasoningToolsJSONCacheVisionWeb

Multiverse Computing (États-Unis)Official−%compactifai/glm-5-2@us

États-Unis

$1.1$1.1

$3.5

$0.22

ReasoningToolsJSONCacheVisionWeb

Tencent Cloud (Asie)Official−%tencent/glm-5.2

Asie

1M

$1.4$1.4

$4.4

$0.26

ReasoningToolsJSONCacheVisionWeb

DatabricksOfficial−%databricks/databricks-glm-5-2

Monde

1M

$1.4$1.4

$4.4

$0.14

ReasoningToolsJSONCacheVisionWeb

Cloudflare (CF/ZAI-ORG/GLM-5.2)Official−%cloudflare/@cf/zai-org/glm-5.2

CF/ZAI-ORG/GLM-5.2

262K

$1.4$1.4

$4.4

$0.26

ReasoningToolsJSONCacheVisionWeb

Mistral AI (Europe)Official−%mistral/glm-5-2

Europe

1.05M

$1.4$1.4

$4.4

$0.14

ReasoningToolsJSONCacheVisionWeb

Together AIOfficial−%together_ai/zai-org/GLM-5.2

Monde

1.05M

$1.4$1.4

$4.4

$0.26

ReasoningToolsJSONCacheVisionWeb

Z.ai (Asie)Official−%zai/glm-5.2

Asie

1.05M

$1.4$1.4

$4.4

$0.26

ReasoningToolsJSONCacheVisionWeb

NebiusOfficial−%nebius/zai-org/GLM-5.2

Monde

432K

$1.4$1.4

$4.4

$

ReasoningToolsJSONCacheVisionWeb

TensorX (Europe)Official−%tensorx/z-ai/glm-5.2

Europe

1.05M

$1.5$1.5

$4.5

$0.375

ReasoningToolsJSONCacheVisionWeb

GreenPT (Europe)Official−%greenpt/glm-5.2

Europe

1M

$1.7442$1.7442

$5.1764

$0.4501

ReasoningToolsJSONCacheVisionWeb

Scaleway (Europe)Official−%scaleway/glm-5.2

Europe

256K

$2.0255$2.0255

$6.1891

$

ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token

0.51 s

Together AI

Lowest latency

1.78 s

Together AI

Highest throughput

139.97 tok/s

Together AI

Best availability

100%

Tencent Cloud (Asie)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

DeepInfra (États-Unis)

2.1 s

31.69 s

138.9 s

55.94 tok/s

100%

47.73%

5.26%

0%

Qwen

3.14 s

22.41 s

80.55 s

68.22 tok/s

99.86%

89.74%

27.41%

1.16%

FlexAI

2.64 s

5 s

30.22 s

74.64 tok/s

97.66%

92.18%

18.68%

0%

Multiverse Computing

2.42 s

35.91 s

148.6 s

92 tok/s

99.33%

29.81%

93.64%

0%

Multiverse Computing (États-Unis)

s

tok/s

%

Tencent Cloud (Asie)

2.57 s

6.85 s

15.76 s

57.94 tok/s

100%

46.57%

0%

Databricks

s

tok/s

%

Cloudflare (CF/ZAI-ORG/GLM-5.2)

s

tok/s

%

Mistral AI (Europe)

1.1 s

2.21 s

10.37 s

94.28 tok/s

99.95%

93.39%

4.08%

0%

Together AI

0.51 s

1.78 s

23.23 s

139.97 tok/s

100%

90.03%

0.46%

0%

Z.ai (Asie)

3.96 s

10.34 s

76.44 s

42.57 tok/s

92.72%

45.09%

9.18%

0%

Nebius

s

tok/s

%

TensorX (Europe)

1.7 s

3.43 s

36.18 s

89.42 tok/s

100%

89.83%

0%

GreenPT (Europe)

s

tok/s

%

Scaleway (Europe)

0.97 s

4.29 s

64.16 s

52.67 tok/s

80.62%

0%

80.69%

0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GLM-5.2 with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

curl https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "", "messages": [{"role": "user", "content": "Hello!"}]}'

const response = await fetch("https://api.edenai.run/v3/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_EDENAI_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
console.log(await response.json());

Questions about GLM-5.2

How much does GLM-5.2 cost?

On Eden AI, prices for this model start at $0.75 per million input tokens and $2.4 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

What is the context window of GLM-5.2?

Up to 1.05M tokens, depending on the endpoint.

Which providers serve GLM-5.2?

15 endpoints from 14 providers, available in: Monde, Asie, Europe, États-Unis. All of them are called with the same Eden AI API key.

Can I run GLM-5.2 in the EU?

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

How fast is GLM-5.2?

Over the last 30 days, the fastest first token was 0.51 s (Together AI) and the highest throughput was 139.97 tokens per second (Together AI).

More from Z.ai

Other Z.ai models you can call with the same key.

See all Z.ai models

Aucun élément.