Chat completions

curl https://api.albastov.com/v1/chat/completions \
  -H "Authorization: Bearer $ALBASTAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-27b",
    "max_tokens": 100,
    "messages": [
      {"role": "system", "content": "Answer in one line."},
      {"role": "user", "content": "Give me three names for a grey cat."}
    ],
    "chat_template_kwargs": {"enable_thinking": false}
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.albastov.com/v1",
    api_key=os.environ["ALBASTAR_API_KEY"],
)
reply = client.chat.completions.create(
    model="qwen3.8-27b",
    max_tokens=100,
    messages=[
        {"role": "system", "content": "Answer in one line."},
        {"role": "user", "content": "Give me three names for a grey cat."},
    ],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(reply.choices[0].message.content)

const res = await fetch("https://api.albastov.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ALBASTAR_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen3.8-27b",
    max_tokens: 100,
    messages: [
      { role: "system", content: "Answer in one line." },
      { role: "user", content: "Give me three names for a grey cat." },
    ],
    chat_template_kwargs: { enable_thinking: false },
  }),
});
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
const reply = await res.json();
console.log(reply.choices[0].message.content);

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.albastov.com/v1",
    api_key=os.environ["ALBASTAR_API_KEY"],
)
reply = client.chat.completions.create(
    model="qwen3.8-27b",
    messages=[{"role": "user", "content": "Name the largest moon of Saturn."}],
    max_tokens=50,
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.albastov.com/v1",
  apiKey: process.env.ALBASTAR_API_KEY,
});
const reply = await client.chat.completions.create({
  model: "qwen3.8-27b",
  messages: [{ role: "user", content: "Name the largest moon of Saturn." }],
  max_tokens: 50,
  chat_template_kwargs: { enable_thinking: false },
});
console.log(reply.choices[0].message.content);

import os, time
from openai import OpenAI, APIStatusError

client = OpenAI(
    base_url="https://api.albastov.com/v1",
    api_key=os.environ["ALBASTAR_API_KEY"],
    max_retries=0,
    default_headers={"X-LLM-Wait": "0"},  # 503 at once; the loop waits
)
RETRY = {"model_loading", "queued", "gpu-busy", "device_busy"}

def create(deadline_s=900, **kwargs):
    start = time.monotonic()
    while True:
        try:
            return client.chat.completions.create(**kwargs)
        except APIStatusError as e:
            body = e.body if isinstance(e.body, dict) else {}
            code = body.get("code")
            wait = int(e.response.headers.get("Retry-After", "10"))
            late = time.monotonic() - start + wait > deadline_s
            if e.status_code != 503 or code not in RETRY or late:
                raise
            print(f"503 {code}, retrying in {wait} s")
            time.sleep(wait)

reply = create(
    model="qwen3.8-27b",
    max_tokens=60,
    messages=[{"role": "user", "content": "One sentence on patience."}],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(reply.choices[0].message.content)

const RETRY = new Set(["model_loading", "queued", "gpu-busy", "device_busy"]);

async function create(body, deadlineMs = 900_000) {
  const start = Date.now();
  for (;;) {
    const res = await fetch("https://api.albastov.com/v1/chat/completions", {
      method: "POST",
      headers: {
        Authorization: `Bearer ${process.env.ALBASTAR_API_KEY}`,
        "Content-Type": "application/json",
        "X-LLM-Wait": "0", // 503 at once; the loop waits
      },
      body: JSON.stringify(body),
    });
    if (res.ok) return res.json();
    const err = (await res.json().catch(() => ({}))).error ?? {};
    const waitS = Number(res.headers.get("Retry-After") ?? 10);
    const late = Date.now() - start + waitS * 1000 > deadlineMs;
    if (res.status !== 503 || !RETRY.has(err.code) || late) {
      throw new Error(`${res.status} ${err.code ?? ""} ${err.message ?? ""}`);
    }
    console.log(`503 ${err.code}, retrying in ${waitS} s`);
    await new Promise((r) => setTimeout(r, waitS * 1000));
  }
}

const reply = await create({
  model: "qwen3.8-27b",
  max_tokens: 60,
  messages: [{ role: "user", content: "One sentence on patience." }],
  chat_template_kwargs: { enable_thinking: false },
});
console.log(reply.choices[0].message.content);