Quickstart

The GATE/0 gateway can be used in two main ways: via our fully managed cloud service or through a self-hosted local deployment. Both offer seamless integration with minimal code changes, but cater to different operational needs.

• The cloud proxy is ideal for teams who want zero setup, automatic scaling, and enterprise-grade security without managing infrastructure.
• The local proxy gives teams full control over their data and environment — perfect for those with compliance, privacy, or air-gapped requirements.

Choose the path that best suits your workflow.

Using the GATE/0 Cloud Gateway

The easiest way to use GATE/0 is through our fully managed cloud proxy, which is secure, scalable, and requires zero setup. For peace of mind, we never store your payload data — all requests are processed in real-time and immediately discarded after forwarding.

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://gateway.gate.io/v1", # GATE0 cloud proxy URL
    api_key=os.environ.get("GATE0_API_KEY"), # API key provided by GATE0
)

completion = client.chat.completions.create(
  model="openai/gpt-4o", # Model name with provider prefix
  messages=[
    {"role": "user", "content": "Hello, how are you?"}
  ],
  extra_body={
    "metadata": { # Custom labels
        "project":"alpha", 
        "client":"frontend", 
        "env":"prod"
    }
  }
)
print(completion.choices[0].message)

As you can see in the example above, you only need to change 3 lines of code in your existing codebase to start using GATE/0.

• Base URL: Replace it with https://gateway.gate0.io/v1
• API Key: Use the API key provided by GATE/0 instead of your original one
• Model Name: Specify the model with a provider prefix. For example, use openai/gpt-4o instead of gpt-4o

Running GATE/0 Locally

For teams with stringent data security or compliance needs, GATE/0 offers the flexibility of on-premises or private cloud deployment. This allows you to maintain complete control over your data while still leveraging GATE/0’s robust cost tracking, usage analytics, and forecasting capabilities.

docker pull gate0/gate0:latest

docker run \
  -p 4000:4000 \
  -e GATE0_GATEWAY_KEY="your-gate0-gateway-key" \
  gate0/gate0:latest

client = OpenAI(
    base_url="http://localhost:4000/v1", # Local GATE0 proxy URL
    api_key=os.environ.get("GATE0_API_KEY"), # API key provided by GATE0
)