Getting Started
Welcome to the Kinetic Runtime API documentation. Learn how to authenticate and stream messages from our proxy gateway.
Model Specifications
Kinetic Runtime proxies requests directly to the Nvidia-hosted GLM 5.2 model (z-ai/glm-5.2).
Max Tokens
16,384
Default Seed
42
Streaming
Supported (SSE)
Gateway Protocol
OpenAI compatible
API Reference
Kinetic Runtime exposes an endpoint mimicking the OpenAI V1 completions standard.
POST
https://kinruntime.xyz/api/v1/chat/completions
Request Headers
Authorization: Bearer <YOUR_KINETIC_API_KEY>
Content-Type: application/json
Node.js SDK Guide
Use the official OpenAI library by customizing the base URL and API key:
npm install openai
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: 'kin_live_...',
baseURL: 'https://kinruntime.xyz/api/v1',
});
const completion = await openai.chat.completions.create({
model: 'z-ai/glm-5.2',
messages: [{ role: 'user', content: 'Say hello!' }],
stream: true,
});
for await (const chunk of completion) {
process.stdout.write(chunk.choices[0]?.delta?.content || '');
}
Python SDK Guide
Integrate directly into Python applications using the native OpenAI client:
pip install openai
from openai import OpenAI
client = OpenAI(
api_key="kin_live_...",
base_url="https://kinruntime.xyz/api/v1"
)
completion = client.chat.completions.create(
model="z-ai/glm-5.2",
messages=[{"role": "user", "content": "Say hello!"}],
stream=True
)
for chunk in completion:
print(chunk.choices[0].delta.content or "", end="")
PowerShell Integration
Interact with the Kinetic API via PowerShell REST requests:
$headers = @{
"Authorization" = "Bearer kin_live_..."
"Content-Type" = "application/json"
}
$body = @{
model = "z-ai/glm-5.2"
messages = @(
@{ role = "user"; content = "Explain Kinetic Gateway" }
)
} | ConvertTo-Json
$response = Invoke-RestMethod -Uri "https://kinruntime.xyz/api/v1/chat/completions" \`
-Method Post \`
-Headers $headers \`
-Body $body
$response.choices[0].message.content