Deploy AI Models
On Any Hardware

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="any"  # Not required for local
)

response = client.chat.completions.create(
    model="my-model",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True
)

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

const response = await fetch("http://localhost:8000/v1/chat/completions", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    model: "my-model",
    messages: [{ role: "user", content: "Hello!" }]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "my-model",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'