Cost management

How much Nitpick costs, what drives cost, and how to control it.

Nitpick is free. Your LLM provider isn’t. Here’s what to expect.

Pricing baseline

Check anthropic.com/pricing for current rates. Approximate:

ModelInputOutput
claude-opus-4-6~$15/M~$75/M
claude-sonnet-4-6~$3/M~$15/M
claude-haiku-4-5~$1/M~$5/M

Anthropic’s prompt caching charges ~10% of input cost for cached tokens. Nitpick enables caching by default for the skill’s system prompt (~15-20k tokens), which is re-read on every agent iteration.

Per-component cost

ComponentLLM calls?Rough cost
nitpick crawlNo (deterministic Playwright)$0
nitpick run --scope smokeNo$0
Scope inference (iterative)1 call, fast model~$0.01
One simple page (static dashboard)~20 calls$1–2 (with caching)
One complex page (8-field form)~30 calls$2–4 (with caching)
One wizard step~25 calls$1.50–3 (with caching)
Flow test (3 stages)~75 calls$6–12 (with caching)

Run-level estimates

ScopeSizeCost (Opus + caching)Cost (Sonnet + caching)
smoke15 pages$0$0
targeted1 page$1–4$0.30–1
iterative3 pages + 1 flow$10–20$2–5
full15 pages + 1 flow$30–50$8–15

Cost levers

  1. Switch to Sonnet: ~5x cheaper than Opus for most tasks.
  2. Use Haiku for fast_model: scope inference uses this by default.
  3. Cap max_iterations: a misbehaving agent can spiral. Set to 30-50 for CI.
  4. Scope tight: iterative with a specific change description tests only affected pages.
  5. Skip flows unless changed: flows are the most expensive.
  6. Use smoke frequently: free, no LLM.

What caching saves

Before caching: ~$8–12 per page on Opus. After caching: ~$1.50–3 per page on Opus.

The skill’s system prompt (~15-20k tokens) is read on every agent iteration. Without caching, you pay full input cost for it 20+ times per page. With caching, ~90% discount on iterations 2+.

Cache TTL is 5 minutes. Serial iterations within one page hit the cache. Parallel page tests each get their own cache (not shared).

Budget caps

A future release will add llm.max_dollars_per_run. Until then:

  1. Set max_iterations conservatively (30-50)
  2. Start with Sonnet for new apps
  3. Monitor your Anthropic console dashboard
  4. Set account-level spend limits in the provider’s console

Cost vs hiring

A US senior QA engineer costs ~$120-150k/year. Nitpick running a full regression every night with Opus costs ~$1,000-1,500/month ($30/night × 30 days). The delta isn’t the LLM bill it’s that Nitpick runs in parallel, overnight, and doesn’t quit.