GLM-5.3

glm-5.3 by Z.ai Released August 19, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to 35% off
Input from
$0.9 / 1M
Output from
$2.86 / 1M
Cached input from
$0.14 / 1M
Context window
1.05M
Endpoints
14
from 13 providers
Regions
Global, Asia, Europe, United States

About GLM-5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

GLM-5.3 is a chat model by Z.ai, available on Eden AI through 14 endpoints from 13 providers, from $0.9 per million input tokens and $2.86 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

14 endpoints from 13 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
Greenference (Europe)Official−%greenference/glm-5.3
Europe
1.05M
$0.9$0.9
$3
$0.18
ReasoningToolsJSONCacheVisionWeb
DeepInfra (United States)Official−%deepinfra/zai-org/GLM-5.3
United States
1.05M
$0.9$0.9
$4
$0.2
ReasoningToolsJSONCacheVisionWeb
QwenOfficial−35%qwen/glm-5.3
Global
1M
$1.4$0.91
$2.86
$0.182
ReasoningToolsJSONCacheVisionWeb
Multiverse ComputingOfficial−%compactifai/glm-5-3
Global
$1.1$1.1
$3.5
$0.22
ReasoningToolsJSONCacheVisionWeb
Multiverse Computing (United States)Official−%compactifai/glm-5-3@us
United States
$1.1$1.1
$3.5
$0.22
ReasoningToolsJSONCacheVisionWeb
Tencent Cloud (Asia)Official−%tencent/glm-5.3
Asia
1M
$1.4$1.4
$4.4
$0.26
ReasoningToolsJSONCacheVisionWeb
Mistral AI (Europe)Official−%mistral/zai-glm-5-3
Europe
1.05M
$1.4$1.4
$4.4
$0.14
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-glm-5-3
Global
1.05M
$1.4$1.4
$4.4
$0.14
ReasoningToolsJSONCacheVisionWeb
Fireworks AI (United States)Official−%fireworks_ai/accounts/fireworks/models/glm-5p3
United States
1.05M
$1.4$1.4
$4.4
$0.26
ReasoningToolsJSONCacheVisionWeb
Cloudflare (CF/ZAI-ORG/GLM-5.3)Official−%cloudflare/@cf/zai-org/glm-5.3
CF/ZAI-ORG/GLM-5.3
1.05M
$1.4$1.4
$4.4
$0.26
ReasoningToolsJSONCacheVisionWeb
NebiusOfficial−%nebius/zai-org/GLM-5.3
Global
1.02M
$1.4$1.4
$4.4
$1.4
ReasoningToolsJSONCacheVisionWeb
Together AIOfficial−%together_ai/zai-org/GLM-5.3
Global
1.05M
$1.4$1.4
$4.4
$0.26
ReasoningToolsJSONCacheVisionWeb
Z.ai (Asia)Official−%zai/glm-5.3
Asia
1.05M
$1.4$1.4
$4.4
$0.26
ReasoningToolsJSONCacheVisionWeb
TensorX (Europe)Official−%tensorx/z-ai/glm-5.3
Europe
1.05M
$1.75$1.75
$4.5
$0.4375
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
0.46 s
Together AI
Lowest latency
0.42 s
Greenference (Europe)
Highest throughput
119.05 tok/s
Together AI
Best availability
100%
Greenference (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Greenference (Europe)
0.87 s
0.42 s
6.19 s
49.35 tok/s
100%
76.89%
60.71%
100%
DeepInfra (United States)
1.23 s
6.9 s
290.36 s
30.8 tok/s
97.84%
81.86%
26.99%
24.14%
Qwen
2.99 s
5.76 s
40.36 s
37.13 tok/s
99.96%
97.64%
0.04%
5.19%
Multiverse Computing
1.73 s
13.76 s
188.36 s
49.08 tok/s
96.21%
31.79%
28.38%
0%
Multiverse Computing (United States)
1.36 s
8.61 s
153.15 s
33.48 tok/s
97.8%
61.2%
24.23%
0%
Tencent Cloud (Asia)
2.05 s
7.06 s
54.81 s
55.8 tok/s
100%
38.11%
0%
8.7%
Mistral AI (Europe)
1.63 s
3.34 s
52.83 s
81.67 tok/s
99.55%
95.69%
0.67%
1.2%
Databricks
1.7 s
2.21 s
12.95 s
49.45 tok/s
99.86%
93.91%
40.16%
21.74%
Fireworks AI (United States)
1.19 s
11.16 s
260.86 s
55.7 tok/s
100%
93.07%
32.08%
0%
Cloudflare (CF/ZAI-ORG/GLM-5.3)
s
s
s
tok/s
%
%
%
%
Nebius
1.81 s
3.46 s
75.55 s
94.52 tok/s
100%
96.53%
5.83%
0%
Together AI
0.46 s
1.79 s
25.95 s
119.05 tok/s
99.88%
97.52%
0.68%
0%
Z.ai (Asia)
4.76 s
8.52 s
124.37 s
30.19 tok/s
97.94%
68.03%
2.73%
0.84%
TensorX (Europe)
1.85 s
4.54 s
67.46 s
81.76 tok/s
99.54%
81%
15.48%
3.13%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call GLM-5.3 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())

Questions about GLM-5.3

On Eden AI, prices for this model start at $0.9 per million input tokens and $2.86 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 1.05M tokens, depending on the endpoint.

14 endpoints from 13 providers, available in: Global, Asia, Europe, United States. All of them are called with the same Eden AI API key.

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.

Over the last 30 days, the fastest first token was 0.46 s (Together AI) and the highest throughput was 119.05 tokens per second (Together AI).