البثّ

curl -N https://<host>/v1/chat/completions \
  -H "Authorization: Bearer vx_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vorix-flash",
    "stream": true,
    "messages": [{ "role": "user", "content": "Count to five." }]
  }'

data: {"id":"req_9f4d…","object":"chat.completion.chunk","created":1769040000,"model":"vorix-flash","choices":[{"index":0,"delta":{"content":"One"},"finish_reason":null}]}

data: {"id":"req_9f4d…","object":"chat.completion.chunk","created":1769040000,"model":"vorix-flash","choices":[{"index":0,"delta":{"content":", two"},"finish_reason":null}]}

data: {"id":"req_9f4d…","object":"chat.completion.chunk","created":1769040000,"model":"vorix-flash","served_by":"vorix-flash","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":34,"completion_tokens":12,"total_tokens":46,"cost":"$0.000023","cost_micros":23,"estimated":true}}

data: [DONE]

const response = await fetch("https://<host>/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VORIX_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "vorix-flash",
    stream: true,
    messages: [{ role: "user", content: "Count to five." }],
  }),
})

const reader = response.body.getReader()
const decoder = new TextDecoder()
let buffer = ""
let usage = null

for (;;) {
  const { done, value } = await reader.read()
  if (done) break

  buffer += decoder.decode(value, { stream: true })

  // Events are separated by a blank line, and a network chunk may cut one
  // in half — keep the remainder buffered until it completes.
  const events = buffer.split("\n\n")
  buffer = events.pop() ?? ""

  for (const event of events) {
    const line = event.trim()
    if (!line.startsWith("data:")) continue

    const payload = line.slice(5).trim()
    if (payload === "[DONE]") break

    const chunk = JSON.parse(payload)
    if (chunk.error) throw new Error(chunk.error.message)
    if (chunk.usage) usage = chunk.usage

    const delta = chunk.choices?.[0]?.delta?.content
    if (delta) process.stdout.write(delta)
  }
}

console.log("\n", usage)

import json
import os
import requests

with requests.post(
    "https://<host>/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['VORIX_API_KEY']}"},
    json={
        "model": "vorix-flash",
        "stream": True,
        "messages": [{"role": "user", "content": "Count to five."}],
    },
    stream=True,
    timeout=300,
) as response:
    response.raise_for_status()
    usage = None

    for line in response.iter_lines(decode_unicode=True):
        if not line or not line.startswith("data:"):
            continue

        payload = line[5:].strip()
        if payload == "[DONE]":
            break

        chunk = json.loads(payload)
        if "error" in chunk:
            raise RuntimeError(chunk["error"]["message"])
        if "usage" in chunk:
            usage = chunk["usage"]

        delta = chunk["choices"][0]["delta"].get("content", "")
        print(delta, end="", flush=True)

print("\n", usage)