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?

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.

Model costs for Multi-step agent← All archetypes