Help

It runs the prompts you track across the engines your plan includes, repeatedly, and records whether your brand is mentioned, where in the answer, which competitors are named, and which sources were cited. Scores are computed from those stored runs by deterministic code, not by a model. The methodology page publishes the arithmetic.

ChatGPT, Perplexity, Gemini, Azure OpenAI, Claude, Gemini with Search grounding. You choose which engines each prompt runs against, and which are available depends on your plan. CiteTrail measures answers from provider APIs — the models behind these assistants — not scrapes of their consumer apps. The engines page lists the exact API surface behind each name.

A credit is not a check. An answer check is one prompt, one engine, one region, and engines are priced by what they cost to run: Gemini 1, ChatGPT 1, Claude 3, Azure OpenAI 7, Perplexity 8, Gemini with Search grounding 14. Your plan includes a monthly allowance that does not roll over. Top-up credits never expire and are only spent once the allowance is gone. Balance and top-ups live under Settings → Credits.

Yes, from Settings → Billing. Changes take effect at the end of the current billing period, and nothing you have already measured is deleted.

Because the models did. Providers update models, prompts and grounding without notice, and answers vary run to run regardless. That variance is what repeated sampling is for, and it is why confidence reflects sample size.

Email support@citetrail.ai. If you are signed in, the Support Center under Settings routes to the same place.