Skip to main content

​
1. Create an account

Go to Tandemn’s gateway and create an account. Right now, we support signing in with GitHub, Gmail and Apple accounts.

​
2. Generating keys

After signing in, go to the keys page and follow the instructions to generate an API key.

​
3. Create a request!

Here, we show an example of running an inference on Llama 70B. The Python code shows an example without streaming and the cURL command shows an example with streaming. 
import requests

url = "https://api.tandemn.com/api/v1/chat/completions"
headers = {
    "Authorization": f"Bearer <your-api-key>",
    "Content-Type": "application/json"
}
data = {
    "model": "casperhansen/llama-3.3-70b-instruct-awq",
    "messages": [
        {"role": "user", "content": "Hello! Can you explain quantum computing?"}
    ]
}

response = requests.post(url, headers=headers, json=data)
print(response.json())