Python (requests)

import requests
url = "https://umva.net/v1/chat/completions"
headers = {
"Authorization": "Bearer umva_ai_YOUR_KEY",
"Content-Type": "application/json",
"User-Agent": "umva-ai-editor/1.0",
"X-Request-Id": "your-uuid-here",
}
data = {
"model": "", // e.g. umva-code-pro, umva-code-architect, umva-code-fast
"max_tokens": 200,
"messages": [
{"role": "user",
"content": "Write a Python sort function"}
],
"stream": True
}
r = requests.post(url, json=data,
headers=headers, stream=True)
for line in r.iter_lines():
if line:
print(line.decode())

Node.js (fetch)

const response = await fetch(
"https://umva.net/v1/chat/completions",
{
method: "POST",
headers: {
"Authorization":
"Bearer umva_ai_YOUR_KEY",
"Content-Type":
"application/json",
"User-Agent":
"umva-ai-editor/1.0",
"X-Request-Id":
crypto.randomUUID(),
},
body: JSON.stringify({
model: "", // e.g. umva-code-pro, umva-code-architect, umva-code-fast
max_tokens: 200,
messages: [
{role: "user",
content: "Write a Python sort function"}
],
stream: true,
}),
}
);
const reader = response.body
.getReader();
// process SSE stream...

cURL — Non-thinking (Default)

At UMVA, requests are non-thinking by default. No extra parameter needed.

curl -L -X POST https://umva.net/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-H "Authorization: Bearer ${UMVA_API_KEY}" \
-d '{
"model": "", // use GET /v1/models to list
"messages": [
{
"content": "You are a helpful assistant",
"role": "system"
},
{
"content": "Hi",
"role": "user"
}
],
"max_tokens": 4096,
"response_format": {"type": "text"},
"stop": null,
"stream": false,
"stream_options": null,
"temperature": 1,
"top_p": 1,
"tools": null,
"tool_choice": "none",
"logprobs": false,
"top_logprobs": null
}'