from openai import OpenAI
import os

# 💥 Create an OpenAI client, pointed at Muna
openai = OpenAI(
  api_key=os.environ["MUNA_API_KEY"],
  base_url="https://inference.muna.ai/v1"
)

# 🔥 Create a chat completion
completion = openai.chat.completions.create(
  model="@qwen/qwen-3.8-27b",
  messages=[{ "role": "user", "content": "What is the capital of France?" }]
)

# 🚀 Print the result
print(completion.choices[0].message)

import OpenAI from "openai"

// 💥 Create an OpenAI client, pointed at Muna
const openai = new OpenAI({
  apiKey: process.env.MUNA_API_KEY,
  baseURL: "https://inference.muna.ai/v1"
});

// 🔥 Create a chat completion
const completion = await openai.chat.completions.create({
  model: "@qwen/qwen-3.8-27b",
  messages: [{ role: "user", content: "What is the capital of France?" }]
});

// 🚀 Print the result
console.log(completion.choices[0]);

# 🔥 Stream a chat completion
stream = openai.chat.completions.create(
  model="@qwen/qwen-3.8-27b",
  messages=[{ "role": "user", "content": "What is life?" }],
  stream=True
)

# 🚀 Use completion chunks
for chunk in stream:
  ...

curl https://inference.muna.ai/v1/chat/completions \
  -H "Authorization: Bearer $MUNA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "@qwen/qwen-3.8-27b",
    "messages": [{ "role": "user", "content": "What is the capital of France?" }]
  }'

{
  "id": "chatcmpl-6f1c2b9e-4d3a-4b8e-9c1f-2a7d5e8b0c34",
  "object": "chat.completion",
  "created": 1791516000,
  "model": "@qwen/qwen-3.8-27b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 16,
    "completion_tokens": 8,
    "total_tokens": 24,
    "prompt_tokens_details": { "cached_tokens": 0 }
  }
}