Last updated: April 5, 2026 · Pricing & Deployment · by Daniel Ashford

What is Input Tokens?

QUICK ANSWER

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

Output Tokens
The tokens the model generates in its response — the most expensive part of API usage.
Tokens
The basic units of text that LLMs process — roughly 3/4 of a word.
LLM API Pricing
The cost of using language models, typically measured in dollars per million tokens.
Prompt
The text input you send to an LLM to get a response.

See How Models Compare

Understanding input tokens is important when choosing the right AI model. See how 12 models compare on our leaderboard.

View Leaderboard →Our Methodology
← Browse all 47 glossary terms
DA
Daniel Ashford
Founder & Lead Evaluator · 200+ models evaluated