LLM cost archetype

Chatbot with history — LLM cost calculator & pricing model

Like a simple chatbot, but you include previous messages in every new prompt so the LLM 'remembers' the conversation. The more turns, the bigger (and more expensive) each call gets.

Does this sound like your app?

Real-world example

An AI sales assistant that qualifies leads over a multi-turn conversation. By turn 8, the prompt includes the system prompt + 7 prior exchanges — easily 4,000–6,000 tokens per call.

Default cost profile

Calls per request
1
Batch-eligible
no
Avg input tokens
3000
Avg output tokens
600

Assumes 1 LLM call per user message, but input tokens are higher (~3,000) because conversation history is included in every prompt. Token usage grows over the session — the 3,000 figure is an average across early and late turns. Prompt caching is valuable here since the system prompt and early history are re-sent on every call. Not batch-eligible.

Rough cost

$10–150/mo at 100–1,000 users/day. Grows fast with session length.

Red flag

If conversations are always 1–2 turns, use Simple chatbot instead.

Model costs for Chatbot with history← All archetypes