Skip to main content
Welcome to the Passy API reference documentation. Passy provides unified access to 70+ AI models through OpenAI-compatible and Anthropic-compatible REST APIs.

Base URLs

Passy supports two API formats:

OpenAI Format

https://api.passy.ai/v1
Compatible with OpenAI SDKs and tools

Anthropic Format

https://api.passy.ai/
Compatible with Anthropic SDKs and tools

Authentication

All API endpoints require authentication using one of these methods:
Authorization: Bearer YOUR_API_KEY
Get your API key from the Passy Dashboard.

Core Endpoints

Text Generation

OpenAI-compatible chat API with streaming, function calling, and vision support

Anthropic

Anthropic-compatible API with extended thinking, tools, and prompt caching

Models

List all AI models with capabilities, pricing, and context windows

Advanced Features

Streaming

Real-time streaming responses with Server-Sent Events

Function Calling

Enable AI to interact with external tools and APIs

Setup Guide

Comprehensive setup guide and security best practices

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.passy.ai/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)

Rate Limits

Rate limits vary by plan tier:
This is test Rate Limits
TierRequests/minTokens/minConcurrent
Basic6090K10
Pro300450K40
EnterpriseCustomCustomCustom

SDK Support

Passy is compatible with popular AI SDKs:
  • Python: openai, anthropic, langchain
  • JavaScript/TypeScript: openai, @anthropic-ai/sdk
  • Go: go-openai
  • Ruby: anthropic-rb
  • Rust: async-openai
  • Java: openai-java
  • C#: OpenAI-DotNet

Need Help?

Developer Docs

Comprehensive guides and tutorials

Models Catalog

Browse all 70+ available models