PromptPinchAI cost glossary.
Plain-language definitions of the terms behind your AI bill.
- AI API
- A way for software to send a request to an AI model run by a provider such as OpenAI, Anthropic or Google, and receive an answer. Providers charge for each request.
- Token
- The unit AI providers use to measure text and bill for it. A token is a small piece of a word. Longer prompts and longer answers use more tokens and cost more.
- Input tokens and output tokens
- Input tokens are the text you send to the model. Output tokens are the text it writes back. Most providers price them separately, and output tokens usually cost more.
- Prompt
- The instructions and context an app sends to an AI model with each request, such as a customer question plus guidance on how to answer.
- AI gateway
- A service that sits between your applications and AI providers. Apps send their requests to the gateway, which forwards them to the provider and records usage and cost.
- Base URL
- The web address an app uses to reach an AI provider. Switching to a gateway usually means changing this one address.
- Provider API key
- A secret code that identifies your account with an AI provider. It lets the provider charge usage to you.
- Verified savings
- The difference between what a request would have cost without optimization and what it actually cost, recorded request by request so it can be audited.