FP&A for AI spend
Your AI bills reconciled, priced and traced to the features and customers behind them.
Product
Spend by provider, model and feature, with billed and estimated kept apart.
Every request tied to the customer or team it served, with cost against revenue.
Your own token mix priced on other models, next to an intelligence score for each.
Next month as a range from p10 to p90, not a single guess.
Limits per feature, team or customer, with a warning before the month ends.
Answers cite the numbers they used.
Why did spend rise last week?
Spend rose 14% week over week. Most of the increase came from the support-bot feature on claude-sonnet-5-5[1], mainly for Acme Corp[2].
Sample data The conversation is an example.
Security
Pricing
Every feature is included, and there is no credit card to enter. If paid plans are introduced later, you'll be told before anything changes.
Everything
Free for a limited time. No credit card.
FAQ
AI Spendbook is financial planning and analysis (FP&A) software for AI spend. It shows what a company spends on AI providers, attributes the cost to customers, features and teams, compares models on the company's own usage, forecasts spend with ranges, and answers questions with citations to the underlying data.
Anthropic and OpenAI connect through their admin usage and cost APIs. Google Gemini connects through the Cloud Billing export to BigQuery. Any other provider can be added with CSV or JSON imports, the Python SDK (pip install spendbook) or the HTTPS ingestion API.
Provider billing sets the total for each day and provider. Request-level telemetry from your app or the SDK explains that total by customer, feature and user. The two are never added together. Billed spend that telemetry does not cover is shown as unattributed, and days the provider has not billed yet are labelled as estimates.
Usage and cost reports from provider admin APIs, the Cloud Billing export for Gemini, the tables or collections you map in Supabase, Postgres or Firestore (only the columns you approve), Stripe invoices if you connect revenue, and events you send with the SDK or API. It only reads from these sources.
Yes. AI Spendbook is free for a limited time, with every feature included and no credit card required. If paid plans are introduced later, users will be told before anything changes.
No, not by default. The SDK sends token counts, model, latency, status and attribution fields. Prompt and completion text is captured only if a workspace admin turns on content capture and the SDK is configured to send it.