Skip to content

Cost and depth ​

bash
npx monkeytest run https://example.com --depth basic
ts
import { resolveDepthPreset, BASIC_PRESET } from '@monkeytestai/monkeytester';

const quick = resolveDepthPreset('basic');
// quick.label === 'Quick pass'
// quick.maxPages === 6
// quick.maxFlows === 5
// quick.focus === 'forms-search-cta'
// BASIC_PRESET.totalBudgetMs === 120_000

Cost follows the page cap, the flow cap, and which model you assign to each phase. Page checks and auth-negative checks do not call the planner. They still open the browser.

Presets ​

DepthIdPagesLLM flowsAlso
Quick passbasic65Focus forms-search-cta. Up to 5 page checks and 6 auth-negative flows, outside the LLM budget. 10s step, 25s flow, 12s page, 120s total.
Shallowshallow43Smaller smoke preset
Broader passstandard86The CLI default caps, when you do not pass --depth
Deeper digdeep1610

--max and --flows override the page and flow caps. Aliases: quick-pass, broader-pass, deeper-dig.

Quick pass is about 10 cases and usually finishes in 1–2 minutes. The 120 second budget is a hard cap: past it, remaining page checks are skipped instead of failing the run.

Estimates for a standard run ​

The figures below are order-of-magnitude estimates for one standard run (8 pages, 6 flows, about 6 steps each), using these token assumptions per call:

PhaseInputOutput
Explorer, per page~2,500~250
Planner, once~6,000~1,500
Runner, per step~1,500~120

That is about 80k input tokens and 8k output tokens. A shallow run is smaller. A deep run is larger. Treat the dollars as a sketch, not an invoice. Provider prices move.

ProviderCheap everywhereBalancedSmart everywhere
OpenAIgpt-4o-mini ~$0.02gpt-4o-mini plus gpt-4o planner ~$0.05gpt-4o ~$0.45
Geminigemini-flash-lite-latest ~$0.01flash-lite plus gemini-flash-latest planner ~$0.02gemini-flash-latest ~$0.05
Anthropicclaude-haiku-4-5 ~$0.08Haiku plus claude-sonnet-4-5 planner ~$0.18claude-sonnet-4-5 ~$0.90
Mistralmistral-small-latest ~$0.03small plus mistral-large-latest planner ~$0.06mistral-large-latest ~$0.18
Groqllama-3.3-70b-versatile ~$0.06same model ~$0.06same model ~$0.06
Local (Ollama)electricityelectricityelectricity

Prompt caching on OpenAI and Anthropic can cut a repeated planner prefix. See Prompt caching. The cheapest lever is a smaller --max, then a smaller --flows, then a smart planner with a cheap runner.

MODEL_PRICES and estimateCostUsd are exported if you want to price a model id in your own host. They are not a bill.

AGPL-3.0-only