A model shows as locked
The model requires a higher plan than the one you are on. Access is decided on the server rather than in the interface, so this is a real entitlement rather than a display bug.
The three most common cases: Claude of any kind on Starter, which includes no Anthropic model at all; Claude Opus or GPT-5.6 Sol on Pro, both of which are Powerhouse; and any newly added model, because the fallback tier for anything not explicitly listed is Powerhouse rather than Pro.
The fix is to upgrade, which takes effect immediately, or to pick a model at your tier. The full mapping of model to plan is in the model reference.
An uploaded PDF produced nothing useful
Almost always because the PDF has no text layer. Text is extracted in your browser before anything is sent, so a PDF that is a photograph or a scan of a page contains no extractable text and the model receives an empty document.
The fix: upload the pages as images (.png, .jpg) instead. Vision-capable models read a page image directly, which works on scans, photographs of documents and handwriting.
A second, subtler version of this: the text extracted fine but the layout was lost, so a complex table came through flattened. For tables specifically, upload the .csv or .xlsx rather than the PDF containing them. The model gets far cleaner structure and the answers get noticeably more reliable. See supported file types.
The answer is out of date or invented
Check whether web search was on. Without it, the model answers from training data with a cutoff months in the past, and it will do so confidently and without flagging the staleness. This is the most common way an AI answer goes quietly wrong.
Turn the search toggle on in the composer and ask again. If the answer changes, the first one was stale. If you are asking about something genuinely obscure, search also matters for a different reason: thin training coverage is precisely the condition under which models invent plausible detail.
For anything you intend to act on, ask a second model the same question in the same conversation. Where two models agree on a specific figure and a source, confidence is reasonable. Where they disagree, at least one is wrong and you would not have known from reading either alone. See using web search.
Credits ran out before the month did
Look at what your default model costs. The single biggest driver is defaulting to an expensive model for routine work: at 10 credits per message, a 2,000 credit Pro allowance is gone in 200 messages, while the same allowance on a 1 credit model is 2,000 messages.
Roughly half the catalogue costs 1 credit and those models handle lookups, rewrites, summaries and formatting perfectly well. Set one of them as your default and switch up deliberately for the messages that decide something.
Two other quiet drains: side-by-side comparison costs two messages rather than one, since both models answer and each bills at its own rate. And the 20 credit rung, Claude Opus 5, GPT-5.6 Sol and Sonar Pro, is worth twenty fast-tier messages each. The credit cost of every model is shown in the picker before you send. Full detail in how credits work.
A conversation will not continue on the model it started on
This happens after a downgrade, or when a trial on a higher plan ends. Downgrading changes which models you can send new messages to, not what you can read, so the conversation is intact and fully readable but that particular model is no longer available to you.
Pick a model at your current tier and continue in the same thread. Context carries across the switch, so you are not starting over. See switching models mid-conversation.
Billing did not stop after I cancelled
Check where you subscribed. A subscription bought inside the iOS or Android app is billed by Apple or Google, and it can only be cancelled in their subscription settings. Cancelling on the website does not touch it, deleting the app does not touch it, and deleting your Whizi account does not touch it.
If you subscribed on whizi.io, cancellation happens in account settings and takes effect at the end of the current paid term rather than immediately, so one further charge is not expected but continued access is. See billing and cancellation.
- Locked model means the plan, not a bug: check the tier mapping
- Empty PDF extraction means no text layer: upload pages as images
- Upload tables as .csv or .xlsx rather than inside a PDF
- Stale answer usually means web search was off
- Cross-check anything important against a second model
- Credits running out usually means an expensive default model
- Store subscriptions can only be cancelled with Apple or Google
Frequently asked questions
Why is a model locked when I am already paying?
Because it needs a higher tier than your current plan. The three usual cases are any Claude model on Starter, which includes no Anthropic model, Claude Opus or GPT-5.6 Sol on Pro, which are both Powerhouse, and recently added models, which default to Powerhouse until they are explicitly promoted. Upgrading applies immediately.
Why did my PDF upload not work?
The most likely reason is that it is a scan or a photograph with no text layer, so browser-side extraction returned nothing and the model received an empty document. Upload the pages as .png or .jpg instead, since vision-capable models can read a page image directly. This also works for handwriting.
Why does the AI keep giving me old information?
Web search is probably off, so the model is answering from training data with a cutoff months ago, and it will not flag that itself. Switch the search toggle on in the composer and ask again. If the answer changes materially, the original was stale rather than wrong in any deeper sense.
I ran out of credits in the second week. What should I change?
Almost certainly your default model. A 10 credit model burns a 2,000 credit Pro allowance in 200 messages, while a 1 credit model gives you 2,000. Set a 1 credit model as the default for routine work and reach for the expensive tier deliberately. If you genuinely need frontier models constantly, Powerhouse at 8,000 credits is the tier that fits.