Skip to main content
Welcome to Passy! Our unified API gives you access to the world’s best AI models (OpenAI, Anthropic, Google, and more) through a single, standardized interface. Let’s make your first request.

​
1. Get Your API Key

First, you’ll need an API key to authenticate your requests.
1

Create an Account

Visit dash.passy.ai/auth to sign up or log in.
Passy Dashboard Login
2

Navigate to API Keys

Go to the API Keys section in your dashboard.
Passy API Keys
3

Generate & Secure Your Key

Click Generate API Key. Copy your new key (it will start with sk-passy-) and store it securely. Treat it like a password!
Keep your API key secret! Never commit it to version control or share it publicly.

​
2. Make Your First Request

Passy is fully compatible with the official OpenAI SDKs. You just need to change the base URL and API key. Choose your preferred language or tool below:
First, install the official OpenAI Python package:
pip install openai
Then, initialize the client and make your first generation request:
from openai import OpenAI

# Initialize client pointing to Passy
client = OpenAI(
    base_url="https://api.passy.ai/v1",
    api_key="your-passy-api-key"  # Replace with your actual key
)

# Make a chat completion request
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "user", "content": "Say hello!"}
    ]
)

print(response.choices[0].message.content)

​
3. The Magic of Unified Models

Passy’s real superpower is instant model switching. Without changing your code structure or SDK, you can evaluate different frontier models simply by altering the model string. 
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Explain quantum computing"}]
)
Want to see what else we support? Browse all 70+ available models in our Models Catalog.

​
What’s Next?

Now that you’ve got the basics down, explore the rest of Passy’s capabilities to build powerful AI applications.

Complete Setup

Learn about environment variables and advanced configuration.

Text Generation

Dive into a detailed walkthrough with complex prompt examples.

Browse Models

Explore all 70+ available models and their specific features.

API Reference

Read the complete technical API documentation.

​
Common Questions

  • General Use: Start with gpt-4o or claude-3.5-sonnet.
  • Long Context/Coding: claude-3.5-sonnet is highly recommended.
  • Speed & Cost: gpt-4o-mini or claude-3-haiku offer incredible performance for basic tasks.
See the Models Catalog for detailed comparisons.
You pay strictly for what you use, without fixed markups. Different models map directly to their underlying provider pricing. Most development testing can be done for under $1.Check your current usage and pricing in the Dashboard.
Yes! Simply change the base URL to https://api.passy.ai/v1 and use your Passy API key. All your existing OpenAI-compatible SDK code will work without any other modification.
Passy handles failover intuitively. If your primary model’s provider experiences downtime, you can seamlessly swap the model parameter to an alternative provider in seconds, ensuring your app stays online.

​
Need direct help?

We’re here to make sure you succeed. Reach out to our team:

WhatsApp Support

Chat with our engineering team instantly.

Book a Call

Discuss enterprise routing, custom GPU servers, or seamless migration assistance.