SideNote ProLocal usage and cost tracking for your AI API spending
Metered API billing is only uncomfortable when it is invisible. SideNote Pro keeps a local ledger of what you used, by provider and model, so you can see the shape of your spending without waiting for an invoice.
What gets recorded
- Token counts. Local estimates, replaced by provider-reported figures when the endpoint returns usage metadata.
- Provenance. Which provider profile and model a request went to, recorded immutably against the response.
- Pricing snapshots. The price used for an estimate is recorded with it, so historical entries do not silently change when a price does.
- A daily ledger. Bounded daily aggregates by provider, model and request category.
- Local cost estimates, derived from the above.
Provider-reported usage takes precedence over local estimates whenever it is available. SideNote Pro recognises the common prompt, input, completion, output and total token fields in final stream events and response metadata. Endpoints that omit usage entirely remain fully supported; you simply get estimates rather than reported figures.
Where prices come from
SideNote Pro ships a small bundled reference price for the default OpenAI model, dated and attributed to the provider's own documentation. That is deliberately narrow: hard-coding a price catalogue for the whole industry would be wrong within weeks.
For anything else, set the price yourself. Each provider profile and model can carry an input and an output price in USD per million tokens, entered in Settings, AI providers. Prices you configure are labelled as user-configured, and historical responses keep the price snapshot they were recorded with.
Get the numbers from your provider's own pricing page at the moment you configure them. Model prices change, and a figure copied from a blog post six months ago will quietly make every estimate wrong.
The optional daily limit
You can set a daily estimate limit in USD. When the day's estimated spend would exceed it, SideNote Pro stops before sending, and it can stop an in-flight stream that crosses the line mid-response.
This is a guard rail against a runaway afternoon, not a billing control. It works from local estimates, so it cannot know about usage from other applications sharing the same API key, and it cannot reconcile against your provider's meter. Treat it as a seatbelt, and set a hard spending cap in your provider's own dashboard as the real limit.
The boundary, stated plainly
SideNote Pro does not query your provider's billing system. It has no access to your provider account beyond the API key you configured, and it never will from the usage page.
Everything here is therefore an estimate, and your provider's invoice is the authority. The estimates are useful for the comparison that matters day to day, which is *is this configuration roughly twice as expensive as that one*, not for reconciling a bill to the cent.
The ledger stores counts, dates, provider and model provenance, request categories and cost aggregates. It does not store prompts, responses, selected text, filenames, document contents, screenshots, image data or API keys. Usage never leaves your PC and is never sent to BediniLabs.
What to do with the numbers
The ledger is most valuable as a feedback loop rather than a report. Run a week on your current configuration, look at which provider and model combinations dominate, and ask whether the expensive ones were doing work that needed them.
Most people find the answer is no, at least partly: heavy models get used for quick rewrites out of habit. That is exactly the pattern reducing your AI API costs is about, and choosing the right model is how you fix it.