# SpendLens AI

> SpendLens AI tracks LLM usage, classifies workloads, detects prompt waste, and identifies safer lower-cost model alternatives.

SpendLens AI is an AI FinOps product operated by Rangkash PTY LTD (ACN 643 391 226), based in Victoria, Australia.

## Core product
- Tracks OpenAI and Anthropic SDK calls without proxying LLM traffic.
- Captures provider, model, token usage, latency, cost, project, endpoint, and Python callsite metadata.
- Automatically groups calls into stable workloads and classifies their task.
- Generates deterministic model-switch recommendations with confidence, quality risk, and projected savings.
- Detects lightweight prompt waste signals including large context, long output, repeated templates, and high input/output ratios.
- Simulates savings against task-compatible models using observed token usage and YAML registry pricing.
- Supports company policy restrictions for model provider families.

## Privacy
- Full user prompts are not sent by default.
- template_only sampling may use system prompts or templates for workload classification.
- off mode uses metadata only.
- Workload classification is cached and does not run on every call.

## Plans
- Free: 1,000 events per billing cycle.
- Starter: 100,000 events per billing cycle.
- Pro: 1,000,000 events per billing cycle.
- Growth: 5,000,000 events per billing cycle.

## Canonical pages
- Home: https://spendlensai.dev/
- Pricing: https://spendlensai.dev/pricing
- Documentation: https://spendlensai.dev/docs
- Python SDK: https://spendlensai.dev/docs/python-sdk
- Privacy: https://spendlensai.dev/docs/privacy
- Sample report: https://spendlensai.dev/sample-report
- Contact: https://spendlensai.dev/contact
- Human-readable product facts: https://spendlensai.dev/llms

## Important limitations
- Savings are estimates, not guarantees.
- Model changes should be evaluated for quality, latency, safety, privacy, residency, and contractual requirements.
- The MVP does not automatically rewrite prompts.
- SpendLens does not collect payment card details; Stripe Checkout and Customer Portal handle billing.