LLM cost archetype
Multi-step agent — LLM cost calculator & pricing model
Your app gives an AI a goal and lets it figure out the steps itself — using tools, making decisions, and iterating until it's done. Each step is a separate LLM call. A task that takes 10 steps costs 10× a single-call task.
Does this sound like your app?
- □The AI decides what to do next based on previous results
- □Your app uses tools — web search, code execution, API calls, file operations
- □A single user task triggers 5 or more LLM calls
- □The number of steps is unpredictable — some tasks take 3 steps, others take 15
Real-world example
An autonomous research agent. User says 'find me the 5 best competitors to my SaaS and summarize their pricing.' The agent searches the web, visits each site, extracts pricing, compares, and writes a summary — 8–12 LLM calls per task.
Default cost profile
- Calls per request
- 8
- Batch-eligible
- no
- Avg input tokens
- 1500
- Avg output tokens
- 600
Assumes 5–12 LLM calls per task (default 8): the agent plans, executes tools, observes results, and iterates. Each call averages ~1,500 input tokens (tool results, prior steps) and ~600 output tokens (next action, reasoning). Call count is the dominant cost driver — the per-call cost matters less than how many steps the agent takes. Prompt caching compounds across steps since the system prompt and task context are re-sent on every call. Not batch-eligible due to the sequential, interactive nature of agent loops.
Rough cost
$50–1,000+/mo at 100–1,000 tasks/day. Call count is everything — reducing agent steps saves more than switching models.
Red flag
If the number of LLM calls per task is always exactly 1–2 and predetermined, this is probably a simpler archetype.