exa-efficiency

Use the cheapest Exa endpoint and setting that delivers the answer; never let a default, an uncapped Agent run, or a forgotten monitor decide the bill.

Prices and behaviour are a 2026-10-27 snapshot of Exa's docs and OpenAPI spec, checked by a live spike of 60 billed requests (about $1.31) whose Search, Contents, Answer, and fixed-effort Agent costDollars matched the pricing page. Re-read against the pricing and billing pages on 2026-11-10: unchanged except Monitors, now $2 per 1K runs (was $15); rate limits unchanged (10 QPS search/answer, 5 deep and agent, 100 contents, 50 active agent runs). Not re-measured live (that spends money). When a figure matters and looks stale, check https://exa.ai/docs/admin/pricing and the response's costDollars, trust those, and report the discrepancy.

Hard rules

Never rely on an expensive default. Send these fields explicitly:
- /search type: unset means auto at $0.007. Send "lite" ($0.004) unless the request needs a parameter lite rejects. Never send legacy fast (same search as lite, $0.007).
- /search contents: unset returns metadata only. Send {"highlights": true}, which is free, instead of unbounded text (172 KB for 5 results live).
- /contents: with no content option it returns full text (45 KB for one page live). Ask for highlights or text.maxCharacters.
- /agent/runs effort: unset means metered auto capped at $5. Send a fixed effort (minimal $0.012, low $0.025, medium $0.10) when the scope is known; otherwise send effort: "auto" with budget.maxCostDollars (minimum $1).
Price before you spend. Run the estimator on any Agent run, monitor, batch, or search above 10 results, and respect a nonzero exit:
```
python3 <skill-dir>/scripts/exa_cost.py estimate agent/runs body.json --budget-usd 1
```