Türkiye ve MENA için GPU tabanlı LLM altyapısı.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmnow.ai/v1",
    api_key="llm-...",
)

stream = client.chat.completions.create(
    model="llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Merhaba!"}],
    stream=True,
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llmnow.ai/v1",
  apiKey: process.env.LLMNOW_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "llama-3.3-70b-instruct",
  messages: [{ role: "user", content: "Merhaba!" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

curl https://api.llmnow.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b-instruct",
    "messages": [{"role": "user", "content": "Merhaba!"}],
    "stream": true
  }'