Overview

Pay-i enables automatic tracking of your GenAI usage with minimal code changes. By simply initializing Pay-i instrumentation, you get immediate visibility into costs, performance, and usage patterns without writing any custom instrumentation code.

This automatic approach (or "auto-instrumentation") provides the fastest path to tracking your GenAI usage across various providers - including language models (LLMs), image generation, audio processing, video analysis, vision capabilities, and Retrieval-Augmented Generation (RAG) technologies.

This guide shows how to configure supported providers for automatic tracking with just a few lines of code.

Looking for deeper insights? Once you have auto-instrumentation working, you can add custom Annotations to gain more detailed business context for your GenAI usage.

SDK Support

Pay-i provides a Python SDK for seamless integration with various GenAI providers. This includes not just Large Language Models (LLMs), but also:

• Image Generation & Vision: Process and create images with vision-capable models
• Audio Processing: Speech-to-text, text-to-speech, and audio analysis
• Video Analysis: Process and analyze video content
• Multimodal Models: Work with models that can handle multiple input and output types
• RAG Systems: Implement Retrieval-Augmented Generation for knowledge-intensive applications

For other programming languages, you can use the OpenAPI specification to generate client SDKs. The examples in this documentation use the Python SDK, which offers the most comprehensive support and helper functions.

Basic Setup

Setting up automatic instrumentation is straightforward with the payi_instrument() function:

import os
from openai import OpenAI
from payi.lib.instrument import payi_instrument

# Initialize Pay-i instrumentation
payi_instrument()

# Configure provider client normally for direct access
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

Important Note for Streaming: When working with streaming responses, you must read the stream to the end before the response is fully instrumented. Pay-i needs the complete token information to accurately track usage and calculate costs.

Optional Proxy Configuration

If you need to use Block limits that prevent requests from being sent to providers when a budget is exceeded, you'll need to configure Pay-i to route requests through its proxy:

# For proxy-specific features like Block limits
payi_instrument(config={"proxy": True})

See Pay-i Proxy Configuration for complete details on this approach.

Provider-Specific Configuration

Pay-i supports various GenAI Providers that offer capabilities beyond just language models. The table below provides an overview of the supported providers:

These providers support a range of GenAI capabilities including:

• Text Generation & Chat: Generate coherent text and hold interactive conversations
• Embeddings: Create vector representations of text for semantic similarity and search
• Knowledge Retrieval: Retrieve and use information from external sources (including RAG implementations)
• Image Generation: Create images from text descriptions
• Vision & Image Analysis: Process and analyze image content
• Speech Processing: Convert between text and speech
• Multimodal Processing: Work with multiple types of data (text, images, audio) simultaneously

For a complete and up-to-date list of all supported models and Resources for each Provider, refer to the Pay-i Managed Categories and Resources documentation.

Related Resources

• Custom Instrumentation with Pay-i - Adding business context to your tracking
• Pay-i Proxy Configuration - For when you need Block limits
• Pay-i Concepts - Core Pay-i concepts
• Pay-i Examples & Quickstarts