Know where every
AI dollar goes
Track AI spend by team, customer, and feature. Forecast bills and know which products are worth the cost.
Works with the providers you already use
What you get
See where every dollar goes
Every provider. One screen.
OpenAI, Anthropic, Google Gemini, and Vercel AI Gateway in one auto-syncing dashboard. Month-over-month trends and spend breakdowns by model and project, plus AI spend forecast on Pro.
Total Spend
$12,847
+14% vs last month
Total Tokens
In
4.2M
Out
1.8M
Forecast
$18,240
projected month
By Provider
Daily Spend
Every dollar accounted for.
Compare tracked spend against actual invoices. Catch hidden charges and billing errors.
Tracked
$12,847
Billed
$12,903
Drift
-0.4%
$56 untracked spend identified
Know which products are worth the cost.
Attribute AI cost to customers, features, and teams. See exactly which product is driving spend.
acme_corp
support_agent
globex_inc
doc_search
initech
summarizer
acme_corp
summarizer
Know before the bill lands.
Set spend thresholds and spike detectors. Alerts go straight to Slack.
Alert rules
Daily amount - Anthropic
Triggers over $200/day
vs Yesterday - OpenAI
Triggers at 200% of yesterday
Monthly budget - All spend
Triggers over $5,000/month
Recent notification
Daily amount - Anthropic
Triggered at $247.60 → sent to #finance-alerts
Setup
Two lines of code. Five minutes.
Works with Python, TypeScript, Vercel AI SDK, and LiteLLM. Wrap your client, tag your requests, open the dashboard.
import superpenguin as sp
from openai import OpenAI
sp.init(api_key="sp_...")
client = sp.wrap(OpenAI(), metadata={
"customer_id": "acme_corp",
"feature": "support_agent",
"team": "cx",
"environment": "production",
"prompt_key": "ticket_summary",
"prompt_version": "3",
})
# Calls go directly to OpenAI. Cost is tracked automatically.
response = client.chat.completions.create(
model="gpt-5.4",
messages=[{"role": "user", "content": prompt}]
)Two paths in
For finance or engineering. Start where you are.
Spend Dashboard
Plug in your provider admin key. Total spend, model breakdown, and invoice reconciliation. No engineering needed.
- Providers and gateways in a single view
- Automatic billing sync
- Invoice reconciliation
- AI spend forecastPro
Python and TypeScript SDKs
For engineering teams that want per-request granularity. Two lines of code, calls go directly to the provider.
- Per-request cost in real time
- Tag by customer, feature, team, prompt
- No base URL changes needed
- Supports Python, TypeScript, Vercel AI SDK, and LiteLLM
Security
Zero lock-in. Zero data exposure.
No prompts stored. Ever.
The SDK logs token counts, model, latency, and your metadata. Prompt content and responses never touch our servers.
Sub-10ms overhead
Async telemetry. Less than 10ms on non-streaming, less than 5ms TTFT impact on streaming. Your users won't notice.
Your keys stay yours
Calls go directly to the provider. We never see, store, or touch your API keys.
Pricing
Simple, usage-based pricing.
Based on the AI spend you manage through SuperPenguin.
Free
$0 / mo
For individuals getting started
- Up to $2K managed spend
- All dashboard features
- Per-request attribution (SDK)
- Reconciliation
- Email support
Growth
$30 / mo
For small teams shipping AI
- Up to $5K managed spend
- Everything in Free
- 3 team members
- Slack cost alerts
- Priority support
Pro
Most popular$200 / mo
For teams scaling AI in production
- Up to $20K managed spend
- Everything in Growth
- 10 team members
- AI spend forecast
Enterprise
Custom
For organizations with high volume
- $20K+ managed spend
- Everything in Pro
- Unlimited team members
- SAML SSOComing soon
Questions
Know if your AI spend
is worth it.
Spend visibility for finance. Per-request attribution for engineering. Five-minute setup.
Start tracking for freeNo credit card. No meetings. No vendor lock-in.