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?
- □Users have multi-turn conversations — the AI refers back to earlier messages
- □You pass conversation history into every API call
- □Sessions can last 10+ messages
- □Users expect the AI to remember what they said earlier in the same chat
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.