Skip to content
mathbehind

Why AI Chat Costs Grow Faster Than Conversation Length

Every new message in a chat resends the whole conversation as input. That makes long conversations much more expensive than the sum of their messages.

By Muhammad Ahmad. Published . 1 min read.

Want to run your own numbers?AI Feature Cost CalculatorOpen the calculator

When you build a chat feature on an AI API, it is natural to estimate cost per message. That estimate will be too low, because AI model APIs don't remember earlier messages on their own. To keep the conversation going, your app sends the whole history again with every new message.

How input grows

Imagine a chat with a 1,000-token system prompt, where each user message is about 200 tokens and each reply about 300. On the first turn, you send 1,200 tokens. On the second, you send the system prompt, the first exchange and the new message: 1,700 tokens. Each turn adds another 500.

By the tenth message, a single request carries 5,700 input tokens, even though the new message is only 200 of them.

Input tokens across a 10-turn conversation
  1. If nothing were resent

    10 × 1,200equals12,000 tokens

  2. Earlier turns resent

    500 × (0 + 1 + 2 + … + 9)equals22,500 tokens

  3. Actual input sent

    12,000 + 22,500equals34,500 tokens

What it costs

At $2 per million input tokens and $10 per million output tokens, the 34,500 input tokens cost $0.069 and the 3,000 output tokens cost $0.03, for about $0.10 per conversation. If history were not resent it would be about $0.054. Across 1,000 conversations a month, that is roughly $99 instead of $54.

Because the resent history grows with every turn, doubling the length of conversations more than doubles their cost.

Ways to keep it under control

  • Prompt caching: many providers charge less for input that repeats from one request to the next, such as a long system prompt.
  • Summarising: replace older turns with a short summary once a conversation gets long.
  • Trimming: drop the oldest messages beyond a certain length, if the task allows it.
  • Shorter replies: output tokens are priced higher and also become input on the next turn.

Tip: When you estimate costs, model a realistic conversation length rather than a single message. Averages from real usage logs are best once you have them.