Costiva
Home New to AI
Tools
All 47 tools → Features Use cases Live demo Impact analytics Pricing Blog FAQ About
Measure. Prove. Build.

Know what your AI costs. Prove what it's worth.

Costiva tracks your AI spend across providers, measures the impact of what you ship, and gives you 47 free tools to plan, build, and test with confidence.

47 free tools · 12 models tracked · pricing verified Aug 12, 2026
The Costiva dashboard showing Anthropic API spend, tokens, and AI ROI by KPI
Impact analytics before/after comparison after a marked deployment

Most teams guess. Costiva closes the loop.

Plan with a free tool, build it, test it, keep it governed — then measure what actually happened and start again.

New to AI?

Find out exactly what AI can do for your business — in about 15 minutes.

  • Tell us about your business in your own words — no tech knowledge needed.
  • Get a personalized report: what to try first, what to skip, and what it could save you.
  • Track your results over time so you know what’s actually working.

Built for businesses with under 100 people.

Sample Northfield Plumbing & Heating · 10 to 24 people

Your top 5: what to try first

  1. 1 Friendly payment reminders Quick win · Bookkeeping and finance
  2. 2 Draft replies to common customer questions Quick win · Customer service
  3. 3 Turn job notes into a polished quote Quick win · Sales

Could free up: about 3.5–12.5 hours a week — roughly $6,950–$36,000 CAD a year. An estimate from the owner’s own answers.

Tools to plan, build, and test with confidence

Answer a few questions, get a ready-to-use result — no account required.

New to AI: Discovery

Describe your business in your own words and get a personal AI plan: what to try first, what it could save you, and how to track it.

Try it free
Free · no signup

AI Readiness Scorecard

Score your readiness to invest in AI across five dimensions, find the one thing actually holding you back, and get a dated 90-day plan to fix it.

Try it free

AI Risk Assessment Generator

Turn a description of an AI system into a structured risk assessment — suggested tier, risks, mitigations, and a monitoring plan.

Try it free
Free · no signup

Batch API Suitability Checker

Describe a workload and get a plain verdict on whether it fits the Batch API — suitable, partially suitable, or not — with the dollar saving and the queue-time trade-off.

Try it free

AI Budget Guardrail Builder

Turn a monthly AI budget into concrete alert thresholds, a forecast-based early warning rule, and an escalation ladder with named roles.

Try it free
Impact analytics

Deltas with caveats, not causality theater

Mark when you deploy a change, and Costiva compares your usage and cost before versus after — flagging a volume shift when one would make the raw numbers misleading. It measures what changed, not what to credit for it.

See how impact analytics works
A deployment marker's before/after impact comparison, with sample sizes shown

Measure across providers, not just one

The Cost Estimator, Token Counter, and Model Picker compare 12 current models across Anthropic, OpenAI, and Google — each price checked by hand, not scraped and trusted blindly. Every model shown was last verified Aug 12, 2026.

Estimate your costs

How it works

Connect a read-only Anthropic Admin key

1. Connect a read-only Admin key

No code changes — Costiva reads your usage and cost through Anthropic's Admin API.

Marking a deployment on the Deployment markers page

2. Mark what you deploy

One label and a timestamp — from an asset's page or right here.

Before and after metrics for a marked deployment

3. See what changed

Cost, tokens, and cache efficiency, before versus after — with sample sizes shown.

Simple, usage-based pricing

Free
Free
Pro
Free
Team
Free

Frequently asked questions

A read-only Anthropic Admin API key. Costiva reads usage, cost, rate-limit, and Claude Code analytics data through Anthropic's Admin Usage & Cost API — never your prompts or completions, since that API does not expose them. The key is stored encrypted and used only to fetch that data on your behalf.

Yes — the Cost Estimator, Token Counter, and Model Picker never call an AI model and are unlimited on every plan, including Free, with no account required. The tools that do call a model (like the CLAUDE.md Generator) are free up to a daily limit per email address.

The Cost Estimator, Token Counter, and Model Picker compare pricing and behavior across Anthropic, OpenAI, and Google models — not just Claude. Usage and cost monitoring on the dashboard is Anthropic-only today, read through the Admin Usage & Cost API.

Nothing is ever deleted or hidden. All of your existing saved assets and versions remain fully viewable and downloadable — a lower plan only limits creating new ones beyond its cap.

It scores every current model from every provider against the same published criteria — see the full methodology and scoring matrix. When two models score close enough, it says so and recommends both rather than forcing a single winner.

Start free — 47 tools, no card required

Register with just an email address. Connect a read-only Admin key whenever you're ready.

Get started free