Overview

nCompass Technologies is one of the fastest and most reliable AI inference provider on the market and the foundation for building AI apps that are powered by open source AI models.

We follow the OpenAI API standard, so the only two things you need to change from your existing AI inference calls is the URL and the Model name.

We support:

• Text and Prompting
• Images and Vision
• Structured Outputs

Quick Start

Follow these steps to get started quickly with our serverless OpenAI-compatible API.

Step 1: Set Up Your Account

1. Go to the nCompass Console .
2. Sign up or log in to your account.
3. Navigate to API Settings .
4. Generate a new API key. Keep this key secure, as you’ll need it to authenticate your requests.

Step 2: Make Your First API Call

To test the API, use the following code examples. Replace YOUR_API_KEY with your actual API key from the console.

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.ncompass.tech/v1",
    api_key="YOUR_API_KEY",
)
 
completion = client.chat.completions.create(
    model="meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
 
print(completion.choices[0].message)

curl https://api.ncompass.tech/v1/chat/completions \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
    "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
    "messages": [{"role": "user", "content": "Hello!"}]
    }'

Step 3: Explore Further

Refer to OpenAI’s documentation  for more examples.