Up to 500 prompts across up to 6 models, or typed questions about every row of a CSV, answered by Jev.
Jev answered 6 rows. 2 cells are unsure: check them by hand.
| review | sentiment | delivery_problem | urgency |
|---|---|---|---|
| Arrived two days early and the bottle was perfect. | positive | no | No reply needed |
| The wine was great but the box was crushed. | mixed | yes | Unsure |
| Never got my order and support did not reply. | negative | yes | Reply today |
| Tastes fine, a bit expensive for what it is. | mixed | no | No reply needed |
| Cork broke, but they sent a new bottle within a week. | mixed | Unsure | No reply needed |
| Third order this year, still my favorite shop. | positive | no | No reply needed |
Each one opens the studio with the text, settings and models filled in.
GEO check, Ask Jev about each row, Test a prompt change or Pick a model. Each fills in the prompts, the instruction and the models.
Paste one prompt per line or upload a CSV. For a GEO check, enter your website and we write the buyer questions.
Every job ends with its own report and a CSV export.
In the run above, Jev answered 18 cells on 6 reviews and marked 2 as unsure: how urgently a crushed box needs a reply, and whether a broken cork counts as a delivery problem. Those are the cells a person should check.
Jev questions cost 1 credit per 10 rows. Prompt jobs cost each model's credits per prompt, shown before you run, and a GEO check's question step is 2 credits. Credits never expire, and your first 20 are free.
No plan, no seat, no monthly minimum, nothing to cancel. You buy credits once and they never expire, every model shows its cost before you run it, and we refund any run that does not finish.
Free
Try Keimodel with no commitment.
Starter
$0.05 per credit
Top up when your free credits run low.
Pro
$0.04 per credit
Best value for regular users.
Max
$0.035 per credit
For power users running many comparisons.
Most model responses cost 1 to 5 credits · A very long prompt or answer costs 1 credit per $0.035 of model cost · The synthesis is priced separately
Every model carries its credit cost in the picker and its real input and output price per million tokens on the panel, and the total for the lineup you have built sits under the Run button. We meter nothing after the fact.
Add an OpenRouter key in Settings and every model response runs on your own account and costs you no credits at all. Only the synthesis, which reads every answer and lists the claims, stays on ours.
Up to 500 prompts or rows per run, across up to 6 models.
It shows how AI assistants answer the questions your buyers ask: we write the questions from your home page, run them with web search, and report which models name you and which sites they cite.
A prompt column (or question), plus an optional system_prompt column, or an expected column for prompt tests. Ask Jev about each row takes any columns.
Typed questions: pick one of your options, place a row on a scale, or answer yes or no. Every answer comes with a confidence, and cells below the cutoff are marked unsure.
Pick a job, add your rows and read the report.