Now in Beta

See every dollar. Control every call.

Ship AI features without losing control of spend, data, or margins. One SDK gives your team cost governance, predictive intelligence, and compliance guardrails — from first prototype to production scale.

0 PII Stored
by Default
30×
Average Customer ROI
0
Proxy Required
Integrations

Works with every major LLM provider

One SDK wraps them all. Track costs, enforce budgets, and detect anomalies across every provider.

O

OpenAI

GPT-4oGPT-4 TurboGPT-4GPT-4o MiniGPT-3.5 Turbo
A

Anthropic

Claude OpusClaude SonnetClaude Haiku
G

Google

Gemini 1.5 ProGemini 1.5 FlashGemini 2.0 Flash
B

AWS Bedrock

Coming Soon
C

Cohere

Coming Soon
M

Mistral

Coming Soon
Platform

The complete AI cost platform

From visibility to monetization — every tool you need to manage AI spend at scale.

Feature 01

Real-Time Cost Visibility

See exactly where every dollar goes the moment it's spent. Break down costs by feature, model, customer, and environment — with dashboards that update in real time, not end-of-month.

  • Per-feature cost breakdowns (chatbot vs. search vs. summarizer)
  • Per-model spend comparison across OpenAI, Anthropic, Google
  • Per-customer cost tracking with margin analysis
  • Historical trends with daily, weekly, and monthly views
  • Full API request logs with token counts, cost, latency, and metadata
Cost by Feature
chatbot
$4,250
search
$2,100
summarizer
$680
Cost by Model
GPT-4o · 62%Claude Sonnet · 25%Gemini Flash · 13%
Top Customers
CustomerAI CostMargin
Acme Corp$1,240+62%
Initech$4,670-38%
Stark Labs$320+78%
Feature 02

Budget Caps & Enforcement

Set hard spending limits at the org, feature, or environment level. When the budget is hit, calls are blocked automatically — no exceptions, no surprises.

  • Per-environment budgets (prod $10k, staging $1k)
  • Tiered alerts at 80%, 95%, and 100%
  • Emergency override with Slack approval
  • Real-time spend tracking with <1ms SDK overhead
$7,234
of $10,000
chatbot
$4,250
search
$2,100
staging
$184
Feature 03

Anomaly Detection & Auto-Shutoff

ML-powered anomaly detection catches spend spikes that rule-based systems miss. Our models learn your org's normal patterns, and the circuit breaker kicks in before cost spirals.

  • ML anomaly scoring with rolling cost and token z-scores
  • Automatic circuit breaker activation
  • PagerDuty, Slack, and email alerts in <60s
  • Post-incident savings report with prevented cost

Spend / hour

Monitoring
Anomaly detected — chatbotSpend 8.2× baseline. Circuit breaker activated, throttling 50% of requests.
↳ Prevented cost: $9,250
Feature 04

Billing & Revenue Management

Turn AI costs into a revenue line item. Set pricing rules per customer, generate invoices automatically, and export to your billing stack.

  • Flexible pricing rules: markup %, flat rate, free tier, tiered
  • Automated per-customer invoice generation via Stripe
  • CSV export for finance teams and custom billing systems
  • Margin analysis to price AI features profitably
INV-2026-0342
Acme Corp
AI API Usage · Mar 2026
chatbot1,240 calls$186
search890 calls$44
summarizer320 calls$28
Subtotal$258
Markup (25%)$64
Total$322
Sent via Stripe &check;
Feature 05

Agent Session Governance

Know exactly what every agent session is spending in real time. Set budget ceilings in the dashboard that automatically halt sessions before they overspend — admins configure limits, engineers never touch dollar amounts.

  • Per-session spend ceilings enforced in real time
  • Dashboard-configured budgets — no code changes required
  • Per-feature policy overrides (code-gen vs. search vs. chatbot)
  • Full session replay: every call, token count, and cost
Session sess-a7f3
code-gen
Halted
$23.41 / $25.00
Session Calls
#ModelCostTotal
1claude-sonnet$1.20$1.20
2gpt-4o$3.85$5.05
3claude-sonnet$2.44$7.49
...
18gpt-4o$4.12$23.41
Budget limit reached — session halted$23.41 of $25.00 ceiling. 18 calls completed safely.
Feature 06
Scale Plan

Predictive Intelligence

Go from reactive to predictive. ML models trained on your data forecast spend, predict budget breaches before they happen, and surface margin-negative customers before you lose money on them.

  • 30-day spend forecasts with confidence intervals
  • Budget breach prediction with probability scoring
  • Per-customer margin trend analysis with recommended actions
  • Models retrain weekly on your org's data — accuracy improves over time
Spend ForecastML Forecast v1.2
$12k$8k$4k$0
Budget: $10,000
7 days agoToday+30 days
Budget breach predicted in 18 days$10,000 limit · 73% breach probability
Margin Intelligence
CustomerMarginTrendAction
Acme Corp+62%stablemonitor
Initech-38%decliningreprice
Stark Labs+78%growinghealthy
1 customer needs repricing · margin negative in 12 days
Feature 07
Growth+

Data Governance & Privacy

Detect PII, PHI, API keys, and financial data in prompts before they reach third-party LLM APIs. Growth plans get metadata-only detection. Scale adds custom policies, user anonymization, snippet forensics, and full audit trail.

  • SDK-level PII/PHI scanning with zero prompt data egress
  • Metadata-only storage by default, no prompt snippets persisted
  • Role-based access controls for violation details
  • User anonymization with deterministic pseudonyms (Scale)
  • Ephemeral snippets with auto-expiry and full audit trail (Scale)
P0
Metadata Only
No prompt snippets stored
P1
Role-Based Access
Read permissions for violations
P2
User Anonymization
Deterministic pseudonyms
P3
Ephemeral Snippets
Auto-expiry + audit trail
And More

Built for teams that need depth

Every tier includes optimization insights. Scale unlocks ML intelligence and governance.

Optimization Engine

Automated recommendations to reduce spend without sacrificing quality.

  • Model downgrade suggestions with confidence scores
  • Duplicate and redundant call detection
  • Estimated monthly savings per recommendation

Zero-Trust Data Governance

Four layers of privacy hardening protect sensitive data before it reaches third-party LLM APIs.

  • PII, PHI, and secrets detection in prompts
  • Metadata-only storage by default with zero data egress
  • Role-based access, user anonymization, and full audit trail

API Request Logs

Drill into every API call with full token breakdowns, cost, latency, and provider metadata.

  • Paginated log table with expandable row details
  • Filter by provider, feature, and time range
  • Input/output token counts with per-call cost
SDK-First

Three lines to production safety

No proxy. No infra changes. Just wrap your existing calls.

app.py
import modelcost
from openai import OpenAI

# 1. Initialize
modelcost.init(
    api_key="mc_xxx",
    org_id="org-123"
)

# 2. Wrap your provider client
client = modelcost.wrap(OpenAI())

# 3. Use as normal — costs tracked automatically
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": prompt}]
)
Setup

Protected in under five minutes

No infrastructure changes. No proxy. Direct API calls stay direct.

1

Install the SDK

Add our lightweight SDK to your project. Python, Node.js, and Java supported. One dependency, zero config files.

~2 minutes
2

Wrap your AI calls

Add the @track decorator to existing functions. Tag with feature name and customer ID. Your code stays the same.

~3 minutes
3

Set budgets & ship

Configure budget caps and alert thresholds in the dashboard. Deploy. Every call is now tracked, attributed, and protected.

~1 minute
Pricing

Simple, transparent pricing

Starts paying for itself the moment you see your first dashboard.

Starter
$29/mo

For teams exploring AI cost visibility.

  • Cost visibility dashboard
  • API request logs
  • Up to $10k/mo tracked spend
  • 3 budget policies
  • Email alerts
  • 30-day data retention
Start Free Trial
Growth
$299/mo

For teams shipping AI to production.

  • Up to $100k/mo tracked spend
  • API request logs
  • Unlimited budget policies
  • Anomaly detection & auto-shutoff
  • Agent session budgets
  • Per-customer attribution
  • Billing & invoicing
  • PII/PHI detection (metadata only)
  • Slack + PagerDuty alerts
  • 90-day data retention
Start Free Trial
Scale
$599/mo

For companies that need predictive AI cost intelligence.

  • Everything in Growth
  • ML spend forecasting
  • Budget breach prediction
  • Per-customer margin modeling
  • ML anomaly detection
  • Advanced agent governance
  • Zero-trust data governance
  • Custom detection policies
  • Governance audit trail
  • Priority support
Start Free Trial

Start seeing where your AI dollars go.

Full visibility, budget enforcement, and predictive intelligence — live in under five minutes.