Glossary · AI monetization
Token Injection
Inserting ad content into an LLM's token stream as it is generated.
What is Token Injection?
Token injection is the technique of wrapping an LLM's streaming output and inserting sponsored, labelled content into the stream before it reaches the user.
Because it operates on the live token stream, injection preserves the incremental, real-time feel of an AI response while adding a monetization layer keyed on the session and prompt.
Token Injection in context
To understand Token Injection fully, it helps to know the concepts around it. In-Conversation Ads, contextual ads placed inside an AI assistant's response stream rather than around the page. Streaming (SSE), sending an LLM response incrementally, token by token, as it is generated. Session, a grouped sequence of interactions from one user conversation. Prompt, the input text that instructs an LLM what to do.
Together these describe how ai monetization works in practice for an AI app, and where Token Injection fits among them.
Frequently asked questions
Start monetizing in about 5 minutes
Wrap your existing LLM response stream with the Monetzly SDK and earn on every session, no paywall required.