Total API Keys
-
Configured in SQLite
Active Keys
-
Ready for inference
Total Invocations
-
Requests served
Inference Engine
Qwen 2.5 3B
Hallucination rate < 6%
Your Secret API Keys
Use these keys to authenticate against https://platform.sydxai.com/v1
| Name / Purpose | Secret Key Prefix | Created | Expiration | Quota / Invocations | Status | Actions |
|---|---|---|---|---|---|---|
| Loading API keys... | ||||||
Model Parameters
Temperature
0.7
Max Response Tokens
512
Live Playground Console
qwen2.5:3b
AI
Hello! I am Qwen 2.5 (3B) running live on your Sydx AI VPS. Ask me anything or test your prompts here!
Integration Guide & Code Snippets
Connect your API key directly into any client, workflow, or automation platform.
n8n
How to connect in n8n
In your n8n workflow, add a Chat Model or Basic LLM Chain node:
- Open node credentials → select API Key configuration.
- Set API Key to your created
sk-sydx-...key. - In Node parameters, enable Base URL override:
https://platform.sydxai.com/v1
- Set Model Name to:
qwen2.5:3b
Since both n8n and this LLM live on the same VPS, API calls complete with near-zero network latency.
cURL
Direct HTTP Request
curl https://platform.sydxai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-sydx-YOUR_KEY" \
-d '{
"model": "qwen2.5:3b",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
],
"temperature": 0.7
}'
Python
Requests Client
import requests
url = "https://platform.sydxai.com/v1/chat/completions"
headers = {
"Authorization": "Bearer sk-sydx-YOUR_KEY",
"Content-Type": "application/json"
}
data = {
"model": "qwen2.5:3b",
"messages": [
{"role": "user", "content": "Extract customer details as JSON"}
]
}
response = requests.post(url, headers=headers, json=data)
print(response.json()["choices"][0]["message"]["content"])
Node.js
Native Fetch API
const response = await fetch("https://platform.sydxai.com/v1/chat/completions", {
method: "POST",
headers: {
"Authorization": "Bearer sk-sydx-YOUR_KEY",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "qwen2.5:3b",
messages: [{ role: "user", content: "Hello!" }]
})
});
const data = await response.json();
console.log(data.choices[0].message.content);
System Telemetry & Resource Monitor
Real-time status of the VPS CPU, RAM, and inference worker.
Inference Engine
Online (127.0.0.1:11434)
Systemd service active with priority Nice=10
Server RAM Footprint
Loading...
Headroom safe for concurrent workloads
CPU Load Average (1m)
-
2 vCPUs dedicated execution pool