Read the forecast period, type, periodicity, assumptions, per-period line items, and variance tolerance from a financial forecast or projection PDF.
The full guide: Financial forecast periods, line items, assumptions
Need to scale? Create an API key, then run this from your own code or an agent.
Create an API keyFree account required
Upload a file or pick a sample, and see the fields come back.
No signup · nothing stored
A forecast projects forward — it carries assumptions, a comparison baseline, and period-by-period future numbers — whereas an income or cash flow statement reports actual historical results. The extractor reads the forecast type (revenue, expense, cash flow, budget), the forecast period start and end, the periodicity, and the number of periods.
Yes. The free-text assumptions field, a key assumptions table (each assumption's category, description, value, unit, and rationale), the confidence level, the variance tolerance, and any contingency or buffer amount all come back structured.
A line items table returns each line's number, description, account code, the amount for each period, the period total, the prior-period actual, and the variance amount and percentage. A period headers table gives each period's index, label, start and end dates, and days in the period.
The document number and date, the preparer and department, the approval status (draft, submitted, approved, rejected), who approved it and when, the effective date, the revision number, and any prior forecast reference this version supersedes.
One PDF up to 10MB and 100 pages. Processed via the Talonic API for extraction only, not retained for training, and not shared. Export as CSV, XLSX, or JSON.
The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.
See invoice data extraction if you run this for finance and AP teams, or the extraction API if you are building it in.