Skip to main content

Introduction

The Portkey AI Gateway provides a unified API to route requests to 250+ LLMs with blazing fast performance. The API is OpenAI-compatible, making it easy to integrate with existing applications.

Base URL

The base URL for all API requests depends on your deployment:
# Local development
http://localhost:8787/v1

# Portkey Cloud
https://api.portkey.ai/v1

# Self-hosted
https://your-gateway-domain.com/v1

OpenAI Compatibility

The Portkey AI Gateway is fully compatible with OpenAI’s API format. You can use any OpenAI SDK by simply changing the base URL:
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8787/v1",
    default_headers={
        "x-portkey-provider": "openai",
        "x-portkey-api-key": "your-openai-api-key"
    }
)
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'http://localhost:8787/v1',
  defaultHeaders: {
    'x-portkey-provider': 'openai',
    'x-portkey-api-key': 'your-openai-api-key'
  }
});

Request Format

All requests follow the OpenAI API format with additional provider-specific headers:
  • Content-Type: application/json
  • Provider Headers: Specify which AI provider to use
  • Request Body: OpenAI-compatible JSON format

Response Format

Responses follow the OpenAI response format:
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o-mini",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 9,
    "total_tokens": 18
  }
}

Supported Endpoints

The gateway supports all major OpenAI API endpoints:
  • /v1/chat/completions - Chat completions
  • /v1/completions - Text completions
  • /v1/embeddings - Generate embeddings
  • /v1/images/generations - Generate images
  • /v1/images/edits - Edit images
  • /v1/audio/speech - Text-to-speech
  • /v1/audio/transcriptions - Speech-to-text
  • /v1/audio/translations - Audio translation
  • /v1/files - File operations
  • /v1/batches - Batch processing
  • /v1/fine_tuning/jobs - Fine-tuning jobs
  • /v1/realtime - WebSocket realtime API

Rate Limits

Rate limits depend on the underlying provider. The gateway passes through provider rate limit headers.

Versioning

The API version is included in the URL path (/v1/). The gateway maintains compatibility with OpenAI’s latest stable API version.

Build docs developers (and LLMs) love