GLM-5.3 Flash

glm-5.3-flash by Z.ai Released August 27, 2026

ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off

Input from

$0.1238 / 1M

Output from

$0.4375 / 1M

Cached input from

$0.015 / 1M

Context window

1.05M

Endpoints

from 11 providers

Regions

Monde, Asie, Europe, États-Unis

About GLM-5.3 Flash

GLM-5.3-Flash est un modèle multimodal natif développé par Z.ai. Il est adapté au codage efficace et aux tâches d'agent à long terme.

GLM-5.3 Flash est un modèle conversationnel développé par Z.ai, disponible sur Eden AI via 11 endpoints chez 11 fournisseurs, à partir de 0,124 $ par million de tokens en entrée et 0,438 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

11 endpoints from 11 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

GreenPT (Europe)Official−%greenpt/glm-5.3-flash

Europe

$0.1238$0.1238

$0.4951

$0.0248

ReasoningToolsJSONCacheVisionWeb

FlexAIOfficial−%flexai/GLM-5.3-Flash

Monde

1.05M

$0.1312$0.1312

$0.4375

$0.0197

ReasoningToolsJSONCacheVisionWeb

Greenference (Europe)Official−%greenference/glm-5.3-flash

Europe

1.05M

$0.14$0.14

$0.49

$0.028

ReasoningToolsJSONCacheVisionWeb

DatabricksOfficial−%databricks/databricks-glm-5-3-flash

Monde

1.05M

$0.15$0.15

$0.5

$0.015

ReasoningToolsJSONCacheVisionWeb

Fireworks AI (États-Unis)Official−%fireworks_ai/accounts/fireworks/models/glm-5p3-flash

États-Unis

1.05M

$0.15$0.15

$0.5

$0.03

ReasoningToolsJSONCacheVisionWeb

NebiusOfficial−%nebius/zai-org/GLM-5.3-Flash

Monde

1.02M

$0.15$0.15

$0.5

$0.15

ReasoningToolsJSONCacheVisionWeb

Cloudflare (CF/ZAI-ORG/GLM-5.3-FLASH)Official−%cloudflare/@cf/zai-org/glm-5.3-flash

CF/ZAI-ORG/GLM-5.3-FLASH

1.05M

$0.15$0.15

$0.5

$0.03

ReasoningToolsJSONCacheVisionWeb

DeepInfra (États-Unis)Official−%deepinfra/zai-org/GLM-5.3-Flash

États-Unis

1.05M

$0.15$0.15

$0.5

$0.03

ReasoningToolsJSONCacheVisionWeb

Together AIOfficial−%together_ai/zai-org/GLM-5.3-Flash

Monde

1.05M

$0.15$0.15

$0.5

$0.03

ReasoningToolsJSONCacheVisionWeb

Z.ai (Asie)Official−%zai/glm-5.3-flash

Asie

1.05M

$0.15$0.15

$0.5

$0.03

ReasoningToolsJSONCacheVisionWeb

TensorX (Europe)Official−%tensorx/z-ai/glm-5.3-flash

Europe

1.05M

$0.2$0.2

$0.5

$0.05

ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token

0.82 s

GreenPT (Europe)

Lowest latency

2.18 s

GreenPT (Europe)

Highest throughput

113.6 tok/s

Databricks

Best availability

99.96%

Z.ai (Asie)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

GreenPT (Europe)

0.82 s

2.18 s

21.32 s

70.27 tok/s

97.06%

93.22%

5.31%

100%

FlexAI

2.54 s

5.01 s

65.26 s

110.99 tok/s

99.8%

93.07%

0.06%

0.89%

Greenference (Europe)

1.11 s

2.38 s

19.23 s

62.36 tok/s

99.9%

92.68%

2.64%

0.31%

Databricks

1.85 s

7.55 s

108.16 s

113.6 tok/s

99.45%

89.71%

13.39%

7.32%

Fireworks AI (États-Unis)

1.59 s

5.32 s

30.52 s

76.87 tok/s

99.89%

91.62%

2.81%

Nebius

2.62 s

6.68 s

113.51 s

109.4 tok/s

98.74%

43.75%

0.36%

0.94%

Cloudflare (CF/ZAI-ORG/GLM-5.3-FLASH)

tok/s

DeepInfra (États-Unis)

1.3 s

33.43 s

133.49 s

21.25 tok/s

99.63%

51.76%

14.68%

0.12%

Together AI

0.9 s

4.67 s

83.46 s

76.99 tok/s

98.89%

90.33%

1.12%

Z.ai (Asie)

3.63 s

11.79 s

105.83 s

33.59 tok/s

99.96%

61.76%

1.07%

TensorX (Europe)

1.91 s

5.06 s

68.97 s

62.9 tok/s

99.53%

71.9%

0.8%

1.91%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GLM-5.3 Flash 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-5.3 Flash

How much does GLM-5.3 Flash cost?

On Eden AI, prices for this model start at $0.1238 per million input tokens and $0.4375 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

What is the context window of GLM-5.3 Flash?

Up to 1.05M tokens, depending on the endpoint.

Which providers serve GLM-5.3 Flash?

11 endpoints from 11 providers, available in: Monde, Asie, Europe, États-Unis. All of them are called with the same Eden AI API key.

Can I run GLM-5.3 Flash 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-5.3 Flash?

Over the last 30 days, the fastest first token was 0.82 s (GreenPT (Europe)) and the highest throughput was 113.6 tokens per second (Databricks).

About GLM-5.3 Flash

Providers and prices

Performance

Estimate your monthly cost

Call GLM-5.3 Flash with Eden AI

Questions about GLM-5.3 Flash

More from Z.ai