Streaming

curl

curl -N https://api.albastov.com/v1/chat/completions \
  -H "Authorization: Bearer $ALBASTOV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-27b",
    "stream": true,
    "max_tokens": 80,
    "messages": [{"role": "user", "content": "Explain prefix caching in two sentences."}],
    "chat_template_kwargs": {"enable_thinking": false}
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.albastov.com/v1", api_key=os.environ["ALBASTOV_API_KEY"])
stream = client.chat.completions.create(
    model="qwen3.8-27b",
    messages=[{"role": "user", "content": "Explain prefix caching in two sentences."}],
    stream=True,
    stream_options={"include_usage": True},
    max_tokens=80,
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    if chunk.usage:
        print("\n", chunk.usage)

JavaScript

const res = await fetch("https://api.albastov.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ALBASTOV_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen3.8-27b",
    stream: true,
    stream_options: { include_usage: true },
    max_tokens: 80,
    messages: [{ role: "user", content: "Explain prefix caching in two sentences." }],
    chat_template_kwargs: { enable_thinking: false },
  }),
});
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);

const decoder = new TextDecoder();
let buffer = "";
for await (const bytes of res.body) {
  buffer += decoder.decode(bytes, { stream: true });
  let end;
  while ((end = buffer.indexOf("\n\n")) >= 0) {
    const event = buffer.slice(0, end);
    buffer = buffer.slice(end + 2);
    for (const line of event.split("\n")) {
      if (!line.startsWith("data:")) continue; // ": loading ..." comments
      const data = line.slice(5).trim();
      if (data === "[DONE]") continue;
      const chunk = JSON.parse(data);
      if (chunk.error) throw new Error(`${chunk.error.type}: ${chunk.error.message}`);
      const text = chunk.choices?.[0]?.delta?.content;
      if (text) process.stdout.write(text);
      if (chunk.usage) console.log("\n", chunk.usage);
    }
  }
}