Core Concepts

Key concepts for using Pofano.

Overview#

Understanding these core concepts will help you make the most of Pofano.

API Gateway#

Pofano is an API gateway that provides a unified interface to multiple AI model providers. Instead of integrating with each provider separately, you make requests to Pofano, and it routes them to the appropriate backend.

Models#

A model is an AI model you can interact with via the API (e.g., gpt-4o, claude-sonnet-4-20250514, gemini-2.5-flash). Different models have different capabilities, pricing, and rate limits.

Providers#

A provider is an upstream AI service that hosts and serves models. Pofano supports 40+ providers including OpenAI, Anthropic, Google, AWS Bedrock, Azure, and many more.

Tokens#

Tokens are the basic units of text processed by language models. Both input (prompt) and output (completion) consume tokens. Token counts determine your billing and quota usage. Roughly, 1 token ≈ 0.75 words in English.

Quota#

Quota is the usage credit system on Pofano. Each API request consumes quota based on the model's pricing and the number of tokens processed. You can check your remaining quota in the console and top up when needed. For more details, see Billing & Quota.