~glm Latest

~glm-latest by Z.ai Released August 19, 2026
Reasoning · Function calling · Structured output · Prompt caching · EU hosting · Up to 35% off
Input from
$0.2 / 1M
Output from
$0.64 / 1M
Cached input from
$0.018 / 1M
Context window
1.05M
Endpoints
18
from 16 providers
Regions
Global, Asia, Europe, United States

About ~glm Latest

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

~glm Latest is a chat model by Z.ai, available on Eden AI through 18 endpoints from 16 providers, from $0.2 per million input tokens and $0.64 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

18 endpoints from 16 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
Multiverse Computingcompactifai/glm-5-3
Global
$0.2
$0.64
$0.018
Reasoning · Tools · JSON · Cache
Multiverse Computing (United States)compactifai/glm-5-3@us
United States
$0.2
$0.64
$0.018
Reasoning · Tools · JSON · Cache
DeepInfra (United States)deepinfra/zai-org/GLM-5.3
United States
1.05M
$0.9
$4
$0.2
Reasoning · Tools · JSON · Cache
Qwenqwen/glm-5.3
Global
1M
$1.40$0.91
$2.86
$0.182
−35% · Reasoning · Tools · JSON · Cache
sference (Europe)sference/zai-org/GLM-5.3
Europe
1.05M
$1.2
$4.2
$0.26
Reasoning · Tools · JSON · Cache
GreenPT (Europe)greenpt/glm-5.3
Europe
1M
$1.2088
$4.8352
$0.3022
Reasoning · Tools · Cache
Arkane Cloudarkanecloud/zai-org/GLM-5.3
Global
200K
$1.4
$4.4
$0.3
Reasoning · Tools · Cache
Tencent Cloud (Asia)tencent/glm-5.3
Asia
1M
$1.4
$4.4
$0.26
Reasoning · Tools · JSON · Cache
Mistral AImistral/zai-glm-5-3
Global
1.05M
$1.4
$4.4
$0.14
Reasoning · Tools · JSON · Cache
Databricksdatabricks/databricks-glm-5-3
Global
1.05M
$1.4
$4.4
$0.14
Reasoning · Tools · JSON · Cache
Fireworks AI (United States)fireworks_ai/accounts/fireworks/models/glm-5p3
United States
1.05M
$1.4
$4.4
$0.26
Reasoning · Tools · JSON · Cache
Cloudflare (CF/ZAI-ORG/GLM-5.3)cloudflare/@cf/zai-org/glm-5.3
CF/ZAI-ORG/GLM-5.3
1.05M
$1.4
$4.4
$0.26
Reasoning · Tools · JSON · Cache
Nebiusnebius/zai-org/GLM-5.3
Global
1.05M
$1.4
$4.4
$1.4
Reasoning · Tools · Cache
Together AItogether_ai/zai-org/GLM-5.3
Global
1.05M
$1.4
$4.4
$0.26
Reasoning · Tools · JSON · Cache
Z.ai (Asia)zai/glm-5.3
Asia
1.05M
$1.4
$4.4
$0.26
Official · Reasoning · Tools · JSON · Cache
Mistral AI (Europe)mistral/zai-glm-5-3@eu
Europe
1.05M
$1.54
$4.84
$0.154
Reasoning · Tools · JSON · Cache
TensorX (Europe)tensorx/z-ai/glm-5.3
Europe
1.05M
$1.75
$4.5
$0.4375
Reasoning · Tools · Cache
Scaleway (Europe)scaleway/glm-5.3
Europe
256K
$1.978
$6.0439
$
Reasoning · Tools

Performance

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

Fastest first token
0.42 s
Scaleway (Europe)
Lowest latency
0.93 s
Multiverse Computing (United States)
Highest throughput
271.86 tok/s
Scaleway (Europe)
Best availability
100%
sference (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Multiverse Computing
12.83 s
14.97 s
71.7 s
31.53 tok/s
99.89%
84.96%
52.86%
20%
Multiverse Computing (United States)
0.54 s
0.93 s
53.74 s
53.37 tok/s
100%
28.64%
39.29%
100%
DeepInfra (United States)
1.26 s
13.32 s
198.89 s
82.54 tok/s
97.99%
29.67%
93.35%
0%
Qwen
4.33 s
8.95 s
40.5 s
35.03 tok/s
100%
96.88%
0.42%
0%
sference (Europe)
0.53 s
3.67 s
53.08 s
119.14 tok/s
100%
96.04%
0.05%
0%
GreenPT (Europe)
1.02 s
4.11 s
44.06 s
48.2 tok/s
99.94%
94.59%
0.03%
0%
Arkane Cloud
0.96 s
1.71 s
23.65 s
59.33 tok/s
97.62%
51.74%
3.39%
0%
Tencent Cloud (Asia)
1.86 s
3.4 s
47.16 s
15.27 tok/s
100%
10.67%
0%
0%
Mistral AI
1.14 s
3.5 s
107.47 s
105.38 tok/s
99.92%
84.3%
0.46%
0%
Databricks
1.3 s
3.88 s
24.72 s
96.48 tok/s
100%
92.11%
0%
0%
Fireworks AI (United States)
2.04 s
3.76 s
20.06 s
40.83 tok/s
100%
83.19%
0%
0%
Nebius
1.2 s
6.59 s
112.58 s
97.81 tok/s
100%
85.43%
62.68%
0%
Together AI
0.95 s
2.79 s
44.39 s
113.96 tok/s
99.67%
97.04%
33.33%
0%
Z.ai (Asia)
3.22 s
6.17 s
67.35 s
36.5 tok/s
99.9%
96.05%
0.97%
0.02%
Mistral AI (Europe)
1.15 s
4.14 s
125.16 s
104.44 tok/s
99.91%
83.85%
0.38%
0%
TensorX (Europe)
2.19 s
5.74 s
80.31 s
67.17 tok/s
99.59%
77.02%
16.48%
0%
Scaleway (Europe)
0.42 s
1.89 s
21.21 s
271.86 tok/s
100%
0%
80.27%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call ~glm Latest 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": "~glm-latest",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about ~glm Latest

On Eden AI, prices for this model start at $0.2 per million input tokens and $0.64 per million output tokens. Prices differ by endpoint; the providers table lists each one.

Up to 1.05M tokens, depending on the endpoint.

18 endpoints from 16 providers, available in: Global, Asia, Europe, United States. All of them are called with the same Eden AI API key.

Can I run ~glm Latest 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 Latest? Over the last 30 days, the fastest first token was 0.42 s (Scaleway (Europe)) and the highest throughput was 271.86 tokens per second (Scaleway (Europe)).