OpenAI-compatible inference.
Without the GPU ops.

# pip install openai — point it at packet.ai
 
from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.packet.ai/v1",
    api_key="$PACKET_API_KEY",
)
 
resp = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Hi!"}],
    stream=True,
)

# any HTTP client works
curl https://api.packet.ai/v1/chat/completions \
  -H "Authorization: Bearer $PACKET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b",
    "messages": [{"role":"user","content":"Hi!"}],
    "stream": true
  }'

// npm i openai
import OpenAI from "openai";
 
const client = new OpenAI({
  baseURL: "https://api.packet.ai/v1",
  apiKey: process.env.PACKET_API_KEY,
});
 
const stream = await client.chat.completions.create({
  model: "llama-3.3-70b", stream: true,
  messages: [{ role: "user", content: "Hi!" }],
});