Many AI providers use OpenAI-compatible APIs internally (including Nebius, Anyscale, Together AI, Fireworks AI, and others), which means you can easily instrument them with Atla using our OpenAI instrumentation.

​
Quick Setup

Simply use the OpenAI instrumentation method: 
from atla_insights import configure, instrument_openai

# Configure Atla
configure(token="<YOUR_ATLA_INSIGHTS_TOKEN>")

# Instrument OpenAI (works with compatible providers)
instrument_openai()

​
Example with Nebius

import os
from atla_insights import configure, instrument_openai
from openai import OpenAI

# Configure Atla Insights
configure(token=os.environ["ATLA_INSIGHTS_TOKEN"])

# Instrument OpenAI
instrument_openai()

# Configure client to use Nebius (or any OpenAI-compatible provider)
client = OpenAI(
    base_url="https://api.studio.nebius.ai/v1/",  # Provider endpoint
    api_key=os.environ["PROVIDER_API_KEY"]
)

# Now all calls will be automatically traced
response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-405B-Instruct",
    messages=[{"role": "user", "content": "Hello!"}]
)

​
Supported Providers

This approach works with any OpenAI-compatible service:
  • Nebius AI: Studio platform with Llama models
  • Anyscale: OpenAI-compatible endpoint
  • Together AI: OpenAI-compatible API
  • Fireworks AI: OpenAI-compatible interface
  • Any other provider that implements the OpenAI API standard

​
Need Help?

If you encounter issues with your provider: