AI cost intelligence for Bedrock, OpenAI & Anthropic
Follow the money.
Every token of it.
Three providers flow in. Tokkara shows exactly which person, team and model every dollar ends up with, then tells you how to spend less.
Read-only access · No SDK · No code changes
Works with the providers you already pay
- AWS Bedrock
- OpenAI
- Anthropic
The problem
The bill grows. The answer doesn't come.
The Bedrock line on the AWS bill doubled. Nobody could tell me which team did it.
Head of Platform
Finance wants AI cost per product. I have one invoice from OpenAI and three from AWS.
Finance lead
I'm fairly sure we run Opus on jobs Haiku could do. I just can't prove it.
Engineering manager
The product
One lens over every model you pay for.
One run rate across every provider
Bedrock, OpenAI and Anthropic land in one number, with the trend, the forecast and what moved it.
Run rate
$48,210
+18.4%
Forecast
$52,900
month end
Requests
4.1M
30 days
Spend by model, down to the token
Input, output and cache tokens priced exactly, then reconciled against your AWS bill.
Spend by model · last 30 days
Every dollar has a name on it
Attribute cost to people and teams from the identities already in your cloud logs. No SDK wrapper.
Top spenders · sample handles
Catch what shouldn't be in a prompt
Access keys, secrets and personal data flagged in prompts before they become an incident.
Open findings · sample
Then price the fix
The Savings Engine ranks concrete changes by dollars per month and effort, and tracks what you rolled out.
Ranked savings · sample account
-$14,930/mo
What a first report looks like
From a blurry invoice to a ranked list of fixes.
- monthly AI spend analysed
- $0
- addressable with no quality loss
- 0%
- projected savings
- $0/mo
- from connect to first report
- 0h
| Action | Effort | Saving per month |
|---|---|---|
| Route summarisation from Opus to Sonnet | Low | $6,180 |
| Enable prompt caching on the support assistant | Low | $4,120 |
| Cap output tokens on batch classification | None | $2,310 |
| Move embeddings to a cheaper model | Medium | $1,460 |
| Stop retry storms in the search pipeline | Low | $860 |
How it works
Connected in five minutes. Nothing in your request path.
- 1
Connect read-only
Add a scoped IAM role and your OpenAI and Anthropic admin keys. Takes about five minutes.
- 2
We read your logs
Invocation logs and usage APIs you already have. No proxy, no SDK, no code changes.
- 3
Attribute every call
Each request is matched to a person, team and model, then priced to the cent.
- 4
Act on it
Budgets, spike alerts, security findings and ranked savings, all in one place.
Built for every seat
One source of truth, four ways to read it.
AI cost per team and product, every month
- Monthly reports ready for the close
- Budgets with 80% and 100% alerts
- Forecasts before the invoice arrives
Capabilities
Everything between the invoice and the fix.
Per-person attribution
Every call traced to a user and team.
Savings Engine
Ranked fixes priced in dollars per month.
Budgets & alerts
Thresholds and spikes to Slack or email.
Security findings
Secrets and PII flagged in prompts.
Monthly reports
Rollout tracking and proven savings.
SSO & teams
SAML/OIDC sign-in and role-based access.
Privacy controls
Choose what's stored; audit every view.
Pricing
Start free. Pay when it pays for itself.
Starter
Free
for your first assessment
- One read-only connection per provider
- Overview, spend and people views
- First savings report
Team
Most popularContact sales
priced on AI spend analysed
- Everything in Starter
- Budgets, alerts and security findings
- Savings Engine with rollout tracking
- Monthly reports
Enterprise
Custom
for regulated and multi-account orgs
- Everything in Team
- SSO, teams and audit log
- Privacy controls
- Priority support
FAQ
Questions, answered.
Do I need to change my application code?
No. Tokkara reads the logs and usage data your providers already produce. There's no SDK, proxy or gateway in the request path.
What access does Tokkara need?
A read-only IAM role for AWS Bedrock and admin usage keys for OpenAI and Anthropic. You can revoke them at any time.
Do you store prompts?
Only if you allow it. Privacy controls let you keep metadata only, and every access is recorded in the audit log.
How accurate are the costs?
Tokens are priced per model, including cache reads and writes, and Bedrock totals are reconciled against your AWS bill.
Put your AI bill in focus.
Read-only access, results within a day, and no change to your application.