~glm Flash Latest

~glm-flash-latest by Z.ai Released August 27, 2026
Reasoning · Function calling · Structured output · Prompt caching · Image input · Video input · EU hosting
Input from
$0.025 / 1M
Output from
$0.07 / 1M
Cached input from
$0.0132 / 1M
Context window
1.05M
Endpoints
16
from 15 providers
Regions
Global, Asia, Europe, United States

About ~glm Flash Latest

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.

~glm Flash Latest is a chat model by Z.ai, available on Eden AI through 16 endpoints from 15 providers, from $0.025 per million input tokens and $0.07 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

16 endpoints from 15 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)greenference/glm-5.3-flash
Europe
1.05M
$0.025
$0.07
$0.025
Reasoning · Tools · Cache · Vision
FlexAIflexai/GLM-5.3-Flash
Global
1.05M
$0.088
$0.25
$0.0132
Reasoning · Tools · JSON · Cache · Vision
GreenPT (Europe)greenpt/glm-5.3-flash
Europe
1M
$0.1209
$0.4835
$0.0242
Reasoning · Tools · Cache · Vision
Arkane Cloudarkanecloud/zai-org/GLM-5.3-Flash
Global
1M
$0.15
$0.5
$0.03
Tools · Cache · Vision
Mistral AImistral/zai-glm-5-3-flash
Global
1.05M
$0.15
$0.5
$0.03
Reasoning · Tools
Databricksdatabricks/databricks-glm-5-3-flash
Global
1.05M
$0.15
$0.5
$0.015
Reasoning · Tools · Cache · Vision
Fireworks AI (United States)fireworks_ai/accounts/fireworks/models/glm-5p3-flash
United States
1.05M
$0.15
$0.5
$0.03
Tools · JSON · Cache · Vision
Cloudflare (CF/ZAI-ORG/GLM-5.3-FLASH)cloudflare/@cf/zai-org/glm-5.3-flash
CF/ZAI-ORG/GLM-5.3-FLASH
1.05M
$0.15
$0.5
$0.03
Reasoning · Tools · JSON · Cache · Vision
DeepInfra (United States)deepinfra/zai-org/GLM-5.3-Flash
United States
1.05M
$0.15
$0.5
$0.03
Reasoning · Tools · JSON · Cache · Vision
Nebiusnebius/zai-org/GLM-5.3-Flash
Global
1.05M
$0.15
$0.5
$0.15
Reasoning · Tools · Cache · Vision
Together AItogether_ai/zai-org/GLM-5.3-Flash
Global
1.05M
$0.15
$0.5
$0.03
Reasoning · Tools · JSON · Cache · Vision
Z.ai (Asia)zai/glm-5.3-flash
Asia
1.05M
$0.15
$0.5
$0.03
Official · Reasoning · Tools · JSON · Cache · Vision
Mistral AI (Europe)mistral/zai-glm-5-3-flash@eu
Europe
1.05M
$0.165
$0.55
$0.033
Reasoning · Tools
sference (Europe)sference/zai-org/GLM-5.3-Flash
Europe
1.05M
$0.2
$0.6
$0.07
Reasoning · Tools · JSON · Cache · Vision
TensorX (Europe)tensorx/z-ai/glm-5.3-flash
Europe
1.05M
$0.2
$0.5
$0.05
Reasoning · Tools · Cache · Vision
Tsystems (Europe)tsystems/GLM-5.3-Flash
Europe
1M
$0.2198
$0.6593
$0.033
Reasoning · Tools · JSON · Cache · Vision

Performance

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

Fastest first token
0.41 s
sference (Europe)
Lowest latency
1.64 s
Greenference (Europe)
Highest throughput
162.91 tok/s
Databricks
Best availability
100%
Arkane Cloud
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Greenference (Europe)
0.84 s
1.64 s
17.8 s
65.44 tok/s
99.96%
70.19%
1.96%
95.96%
FlexAI
2.01 s
3.98 s
78.31 s
112.51 tok/s
99.28%
91.35%
0.76%
0%
GreenPT (Europe)
0.8 s
2.55 s
19.12 s
59.14 tok/s
99.84%
92.25%
0.34%
0.95%
Arkane Cloud
1.08 s
2.84 s
195.14 s
71.25 tok/s
100%
92.87%
0%
0%
Mistral AI
1.4 s
2.77 s
21.86 s
64.28 tok/s
99.9%
82.67%
0.88%
1.97%
Databricks
2.04 s
7.69 s
19.57 s
162.91 tok/s
99.96%
89.39%
0.06%
78.57%
Fireworks AI (United States)
1.67 s
3.52 s
27.63 s
63.23 tok/s
99.95%
91.13%
0.16%
0%
DeepInfra (United States)
1.81 s
3.03 s
15.2 s
43.36 tok/s
99.96%
91.55%
1.73%
0.03%
Nebius
1.38 s
32.42 s
155.37 s
139.04 tok/s
98.74%
53.19%
0%
1.6%
Together AI
0.85 s
8.25 s
104.29 s
136.86 tok/s
100%
52.31%
0%
0%
Z.ai (Asia)
3.21 s
6.23 s
70.43 s
32.93 tok/s
99.32%
90.84%
1.48%
21.55%
Mistral AI (Europe)
1.39 s
2.78 s
22.24 s
62.29 tok/s
99.89%
82.4%
0.92%
1.34%
sference (Europe)
0.41 s
2.4 s
32.97 s
145.63 tok/s
99.92%
93.55%
1.02%
0%
TensorX (Europe)
1.79 s
4.45 s
40.08 s
69.02 tok/s
99.8%
72.04%
0.21%
0.16%
Tsystems (Europe)
0.93 s
2.05 s
32.75 s
133.22 tok/s
98.81%
86.69%
11.53%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

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

Questions about ~glm Flash Latest

On Eden AI, prices for this model start at $0.025 per million input tokens and $0.07 per million output tokens. Prices differ by endpoint; the providers table lists each one.

Up to 1.05M tokens, depending on the endpoint.

16 endpoints from 15 providers, available in: Global, Asia, Europe, United States. All of them are called with the same Eden AI API key.

Can I run ~glm Flash 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 Flash Latest? Over the last 30 days, the fastest first token was 0.41 s (sference (Europe)) and the highest throughput was 162.91 tokens per second (Databricks).