Last updated: April 5, 2026 · Pricing & Deployment · by Daniel Ashford
What is Input Tokens?
The tokens in your prompt that the model reads — cheaper than output tokens.
Definition
Input tokens are the tokens you send to the model — including the system prompt, user message, documents, and conversation history. They are processed but not generated, making them cheaper than output tokens.
How It Works
Input token costs are typically 3-5x lower than output. Claude Opus 4 charges $15/M for input vs $75/M for output. Strategies to reduce input costs include keeping system prompts concise, using prompt caching, and summarizing conversation history.
Example
If your system prompt is 500 tokens, the user message is 100 tokens, and you include a 2,000-token document, your total input is 2,600 tokens.
Related Terms
See How Models Compare
Understanding input tokens is important when choosing the right AI model. See how 12 models compare on our leaderboard.