The cost of collecting AI answers in-house is rarely the API bill you avoid. It is the engineering time to reach production quality on each engine, plus the maintenance that follows for as long as you run it. Building is the right call when the collection layer is itself your product or you need data no provider returns; the build vs buy comparison covers that decision, and the framework below fills in the numbers behind it.
Consumer AI products such as ChatGPT, Perplexity, Gemini, Copilot, Grok and Google AI Mode show answers that include web search, citations, product cards and local results. Those surfaces live in the consumer applications, not in the model providers' developer APIs. Each of the components below exists once per engine.
You run automated collection against each product and keep throughput inside what each product allows. That is infrastructure to provision, scale, patch and monitor, sized for your peak run.
Each engine renders answers differently: inline citations, grouped sources, shopping cards, maps, follow-up queries. Each needs its own parser, a fixture set, and tests. When an interface changes, the failure can be silent: the run succeeds and a field such as sources comes back empty. Catching that takes data-quality monitoring per field, per engine.
Answers differ by country, and for local intent by region. Reporting per market requires collecting from each market and validating that the stored answers reflect it.
At volume, partial failure is the normal case. You need a queue with priorities, retries that cannot create duplicates, per-run deadlines, result storage and a way to push results to downstream systems. That is a distributed-systems project in its own right.
Each consumer product has its own terms of service. Collecting from them at volume is a decision for your legal and compliance review, per engine, before engineering starts, and again when terms change.
Interfaces change without notice and on no schedule. Somebody owns the pager for each engine.
Team cost, engine count and quality bar vary too much for universal numbers. Fill in this table with your own.
| Variable | Meaning | Your number |
|---|---|---|
| E | Engines you need | |
| B | Engineer-months to reach production quality on one engine | |
| M | Engineer-months of maintenance per engine, per month | |
| C | Loaded cost of one engineer-month | |
| I | Monthly infrastructure: compute, storage, monitoring | |
| R | One-off review and compliance cost | |
| T | Months you plan to run it |
Then:
E × B × C + E × M × C × T + I × T + R
Adjust for three effects the formulas miss:
E × B months pass before the first reliable dataset; for a product that competes on time to market, that delay has its own cost.
Buying is priced in credits per request. As async tasks, the base price per request is:
| Engine | Credits per request |
|---|---|
| ChatGPT | 5 |
| Gemini | 4 |
| Copilot | 5 |
| Google AI Mode | 4 |
| Google Search | 3 |
| Google News | 2 |
Perplexity and Grok are d for now and coming back soon; requests to them are refused and not billed. Synchronous calls add 2 credits each. Some options add to the price: on ChatGPT, +2 once if include.rawResponse or shopping is on (searchQueries and ads are free); on AI Mode, +1 per expanded product cluster, up to 6; on Google Search, +2 per extra page and +2 once for the AI Overview; on Google News, +2 per extra page. Credits are reserved at the maximum and charged at the actual cost on success; failed requests are charged nothing, and queued tasks you clear are never charged. The details are in credits.
20,000 prompts on ChatGPT and Gemini in the US, plus 2,000 Google News queries in 10 markets:
A weekly sweep (4 a month) is 880,000 credits, inside the Growth plan's 1,350,000. A daily sweep is 6,600,000 a month and needs an Enterprise plan. Plan prices and a volume estimator are on the pricing page.
200 prompts on ChatGPT and Gemini in the US, plus 50 Google News queries in 3 markets, weekly (4 runs a month):
Unused monthly credits do not roll over, so size the plan to your steady cadence, not your peak. The cost planning guide covers sampling and cadence choices that change these numbers, and sampling vs census covers when you can run fewer prompts without losing the signal.
Compare the output as well as the price. Each engine returns structured JSON under result, with fields that differ by engine:
text, sources[], and markdown with include.markdown. citationPills[], entities[], shoppingCards[] (with include.shopping), map[]. The searchQueries[] (free with include.searchQueries), inlineProducts[] (with ads[] (with include.ads) fields exist but come back empty on the answers served today.places[].
For volume, tasks go through POST /v1/async/task/batch (up to 500 per request) with idempotency keys and webhooks. Retries, deadlines and queueing are part of the API contract rather than code you maintain; see async tasks.
Buying the collection layer moves engineering to the parts that differ between products:
task.id, and storage; see shopping_cards on Perplexity, shoppingCards on ChatGPT; citation ids 0-based on ChatGPT and 1-based elsewhere), so map them into your own schema once.
SDKs and workflow integrations are listed under integrations; for AI agents, the MCP server exposes each engine as a tool.
| Situation | Lean |
|---|---|
| Answers feed an analytics, SEO or visibility product | Buy |
| You need several engines and several markets | Buy |
| Time to first reliable dataset matters | Buy |
| Collection itself is the product you sell | Build |
| You need a field no provider returns | Build that part, scoped to one engine |
| One engine, low volume, and spare engineering capacity | Either; compare with the framework |
A hybrid also works: buy the engines and markets a provider covers, and build narrowly where you need something specific.
The table version of this comparison is at build vs buy; to run your first prompts, start with the quickstart.