Direct reporting
OpenAI + Anthropic
Connect reporting accounts for provider-reported usage and cost totals. Credentials are encrypted; prompts and code are not requested.
Connect in the dashboard →AI spend, without the blind spots
Every model.
Every dollar.
In view.
Your OpenAI and Anthropic spend, together. Understand the source. Set a budget. Keep the surprises out.
No credit card. Cost and usage reports—not prompts, responses, or source code.
Prefer local detail? Use the optional CLI →
Sample data · not your account
BR / 001All providers · seven-day spend
SAMPLE PERIOD01–07 Sep 2026USD · fixed example
Daily spend · USDDaily allowance $80
$140.00 remaining. Sample only; nothing is saved.
Provider ledger
| Provider | Spend · USD |
|---|
View daily data table
| Sep 2026 | OpenAI | Anthropic | Total |
|---|
01 / Bring the numbers together
One view. Clear sources.
A reporting connection is not a proxy. Choose the right path for your data, with its source kept in view.
Local Relay
Your keys stay local.
Use the local Relay to send aggregate provider reports to your workspace without storing provider keys in the cloud.
Read the Relay setup →Aggregate import + CLI
Detail, on your terms.
Import aggregate usage into the web dashboard. For session, project and agent-level detail, analyze your coding tools with the optional local CLI.
Explore local installation →Local CLI coverage: Claude Code / Cursor / OpenAI Codex / GitHub Copilot / Windsurf / Cline / Aider
02 / From number to next step
Read the spend.
Make the call.
A useful number tells you where it came from—and what to inspect next.
SAMPLE · 7 DAYS$420.00
Start with the whole picture.
See daily spend across reporting accounts. Select a day in the sample above to inspect the same underlying rows.
SOURCE → PROVIDER REPORTNot an estimate.
Keep source beside spend.
Provider-reported totals and local API-equivalent estimates answer different questions. Do not mistake an estimated token cost for a subscription bill.
SAMPLE · $560 − $420$140 remaining
Give the number a boundary.
Set budgets and inspect cost trends. Try the sample budget above; its reference line changes, not your account.
03 / Shared visibility, explicit control
A team view.
Not a view into their code.
Share aggregate provider reporting in a cloud workspace, with explicit roles and owner-managed billing.
Shared provider reporting
Review the provider usage and cost totals connected to your workspace. This is aggregate reporting, not a per-developer or per-project productivity dashboard.
Invitations and roles
Invite admins, members and read-only viewers. Workspace roles govern access to provider connections, budgets and member administration.
Owner-managed billing
The workspace owner reviews paid seats and manages invoices, payment methods and cancellation. Billing changes require explicit review.
Privacy-First Architecture
Cloud reporting does not request prompts or code. An optional Relay sends only configured aggregate usage; pairing and configuration are explicit, not automatic after a CLI install.
How Teams Use It
Start in the browser. Add the reporting sources and people your workspace needs.
1
Open a workspace
Sign in to the cloud dashboard and choose your workspace.
2
Connect reporting sources
Add reporting accounts, import aggregate usage, or explicitly pair and configure an optional Relay.
3
Invite members
On Team, owners and admins invite people with the appropriate workspace role.
4
Review spend and budgets
Inspect aggregate provider spend. Owners and admins manage the workspace budget; budgets do not block provider spending.
Ready for a team-wide cost view?
Start with the free browser dashboard. Compare Team when you need a shared workspace, member invitations and owner-managed seats.
Compare Team PlansEnterprise
Have organizational requirements beyond the published plans? Contact us to discuss fit and availability. No enterprise feature package is promised here.
04 / The optional local instrument
Your machine.
Your session detail.
Keep raw code and sessions local. Install the CLI when you need agent trees, project-level costs and API-equivalent estimates.
brew install --cask burnrate-dev/tap/burnrate && burnrateRelease 2.0.2
Simple, transparent pricing
These plans describe the cloud dashboard. Start free; upgrade for scheduled sync, comparisons, alerts or a shared team workspace. The optional local CLI has separate views, including Sessions and Costs.
Free
$0
forever
- Cloud overview and provider spend ledger
- Up to 3 usage sources, including 1 Relay
- 1 workspace budget
- 30-day history
Pro
$12/month
Optimization outcomes depend on your usage
- Everything in Free
- Unlimited provider and Relay sources
- Provider and model comparisons
- Explainable savings recommendations
- Scheduled sync and alerts
- Unlimited history
- Export to JSON
Best for Teams
Team
$29/seat/mo
For engineering teams
- Everything in Pro
- Shared team workspace
- Aggregate provider reporting
- Member invitations and roles
- Owner-managed seat billing
- Priority support
Per seat, per month. The workspace owner selects seats and reviews the order before checkout.
Start TeamEnterprise
Let’s talk
Contact us to discuss fit
Tell us about your requirements. Scope, availability and any commercial terms need a separate discussion.
Contact SalesDive deeper into local capabilities
Go deeper, locally.
The optional local dashboard adds session, project and agent-level analysis. These local capabilities are separate from web reporting connections.
Cost Breakdown & Plan Value
See exactly what your AI usage would cost on API pricing versus what you pay on your subscription. Track daily spending trends and model-by-model cost distribution.
- Daily API equivalent cost chart
- Model cost breakdown (donut chart)
- Plan value multiplier calculation
- Savings percentage vs API pricing
Session Explorer
Browse every AI session with full metadata — duration, tokens, cost, model, and project. Filter by date, project, or model. Sort by any column to find your most expensive sessions.
- Searchable session history
- Per-session API equivalent cost
- Filter by project, model, date range
- Cache hit rate per session
Provider Comparison
Side-by-side comparison across all 7 providers. Per-provider model breakdowns, efficiency scores, token distribution, and daily cost sparklines.
- Cost-per-session and cost-per-message metrics
- Efficiency scoring (0-100)
- Per-model cost breakdown within each provider
- Daily cost trend sparklines
Optimization Engine
46 rules analyze your usage patterns and suggest concrete, actionable savings — with provider-specific config snippets for each tool. Each rule explains why it matters, how much you can save, and provides one-click config snippets to apply.
- Impact scoring (high/medium/low)
- Estimated monthly savings per rule
- Auto-apply config snippets to CLAUDE.md
- Educational explanations with real-world analogies
Project Analytics
Track costs and usage per project. See which codebases consume the most tokens, set per-project budgets, and identify projects that need optimization.
- Per-project cost and session counts
- Project cost ranking charts
- Budget cap monitoring
- Cross-project comparison
Usage Patterns & Operations
Understand which operations — reading, writing, searching, thinking — consume the most tokens. Identify tool usage patterns and optimize your workflow.
- Operation-level token breakdown
- Tool call frequency analysis
- Context efficiency metrics
- Session depth distribution
Rate Limit Monitoring
See exactly how close you are to hitting rate limits across Claude, Cursor, and Codex. Live utilization bars with color-coded thresholds and reset countdowns.
- 5-hour, daily, and weekly window tracking
- Color-coded utilization (green → yellow → red)
- Reset time countdowns
- Multi-provider limit tracking
Budget Alerts
Set per-project spending caps and burn rate limits. Get desktop notifications when budgets are at risk. Configure Slack webhooks for team-wide alerts.
- Per-project monthly and daily caps
- Burn rate monitoring and projections
- Desktop and Slack notifications
- Budget vs actual visualizations
Agent observability meets cost analytics
Powerful analytics that run entirely on your machine. See what your agents do, what they cost, and how to optimize them.
Subagent Observability
See every subagent Claude Code spawns — what it costs, what tools it uses, how long it runs. Per-subagent cost trees show exactly where tokens go in agentic workflows.
- Per-subagent cost breakdown
- Tool call tracking per agent
- Agent duration and depth analysis
- Zero config — parses local JSONL automatically
Multi-Provider Analytics
Track Claude Code, Cursor, Codex, Copilot, Windsurf, Cline, and Aider in one dashboard. Compare costs across all 7 providers.
Cost Optimization Engine
46 optimization rules analyze your usage patterns and surface concrete opportunities — including provider-specific rules for Claude Code, Cursor, Copilot, Codex, Windsurf, Cline, and Aider. Your result depends on actual tools and usage.
Model Recommendations
AI-powered suggestions for which model fits each project. Stop overpaying for simple tasks.
Operation Cost Breakdown
See exactly which operations -- reading, writing, searching, thinking -- consume the most tokens.
Context Efficiency Analysis
Understand how your context window fills up across sessions. Identify context bloat patterns.
Local-First & Private
Your code and raw session data never leave your machine. Core analytics have no cloud dependency.
Set Budgets. Get Alerts. Stay in Control.
Set per-project spending caps, burn rate limits, and alert thresholds. Get desktop notifications or Slack webhooks when budgets are at risk.
- Per-project monthly and daily caps
- Burn rate monitoring
- Desktop notifications
- Cloud alerts are configured separately on Pro or Team
Plan Usage Limits & Rate Tracking
See exactly how close you are to hitting rate limits across Claude, Cursor, and Codex. Live utilization bars with reset countdowns — never get throttled by surprise.
- Claude 5h / 7-day / Opus window tracking
- Color-coded utilization (green → yellow → red)
- Reset time countdowns
- Cursor & Codex activity monitoring
Local review, optional aggregate sharing
Review session and project analytics on your own machine. Sharing with a cloud workspace requires a separately paired and configured Relay; the local CLI does not automatically create a team reporting feed.
- Local session and project analysis
- Cloud workspace budgets are separate
- Explicit Relay pairing and configuration
- Configured aggregate usage only
AI coding tools are expensive.
Are you getting your money's worth?
Illustrative subscription costs, not current provider quotes. Check each provider’s pricing and compare it with your own local usage.
$100/mo
Claude Max
"But how much of that capacity are you actually using?"
$20/mo
Cursor Pro
"Which features drive the most token usage?"
Pay-per-token
OpenAI API
"Do you know your actual cost per coding session?"
Provider bills are only one perspective.
Cloud reporting shows aggregate provider spend. The optional local CLI adds session and subagent analysis from the local data available.
Capability comparison shown for context; provider offerings change. Local estimates are not provider invoices.
Feature
BurnRate
Anthropic Console
OpenAI Platform
Cursor
Multi-provider tracking
✓
✗
✗
✗
Subagent observability
✓
✗
✗
✗
CLI/IDE tool tracking
✓
✗
✗
✗
Per-project cost breakdown
✓
✗
✗
✗
Optimization recommendations
✓
✗
✗
✗
Model recommendations
✓
✗
✗
✗
Shared workspace (cloud Team plan)
✓
✗
✗
✗
Raw sessions stay local (optional CLI)
✓
N/A
N/A
N/A
The field notes
Better questions.
Better decisions.
Independent tools and research for your next spending decision. Read the blog →
01 / Plan
AI Cost Calculator
Estimate monthly team spend and model a savings scenario. No login or data upload.
Calculate free →02 / InspectAgent Config Scanner
Find risky permissions, unsafe MCP config, and missing approval gates. Files stay in your browser.
Scan free →03 / Research2026 Cost Report
Free PDF with data on what developers spend across seven AI coding tools.
Read the report →04 / Learn5-Day Email Course
Learn to inspect and reduce wasted AI spend. One practical lesson per day, completely free.
Sign up free →Frequently asked questions
What data does BurnRate collect?
The web dashboard stores provider-reported usage and cost totals, account metadata, and product analytics. Reporting credentials are encrypted. BurnRate does not request or store prompts, responses, or source code. The optional CLI processes detailed session data locally.
What is subagent observability?
When Claude Code runs complex tasks, it can spawn child agents that consume tokens independently. The optional BurnRate CLI parses local session data into an agent tree with tools, tokens, duration, and estimated cost—without uploading the underlying prompts or code.
Which AI tools are supported?
The web dashboard currently connects OpenAI and Anthropic reporting accounts. The optional local CLI analyzes Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Windsurf, Cline, and Aider.
How does licensing work?
The web dashboard uses passwordless email sign-in and self-service Stripe billing. The local CLI remains usable without a cloud account for its free local features.
What does the optimization engine do?
Cloud Pro and Team provide explainable provider and model recommendations based on available aggregate usage. The separate local CLI has 46 rules for local session patterns, context accumulation, operation costs and cache efficiency. Any savings figures are estimates, not guaranteed outcomes.
Can I use this at work?
Confirm your organization’s requirements before use. BurnRate is not currently SOC 2 certified. The cloud dashboard handles reporting aggregates and account data; the optional CLI processes raw sessions locally. Team adds a shared cloud workspace with member invitations and roles.
What if I cancel Pro?
Use owner-managed billing settings to review cancellation timing. Once paid access ends, the workspace returns to Free limits: up to 3 usage sources including 1 Relay, 1 workspace budget and 30-day history. Optional local CLI files are separate from cloud billing.
How does team analytics work?
Team provides a shared cloud workspace for aggregate provider reporting, member invitations and server-enforced roles. The owner manages paid seats and billing. An optional Relay sends only explicitly configured aggregate usage; installing the local CLI does not automatically sync developer sessions into a team dashboard.
Is this SOC 2 compliant?
BurnRate is not currently SOC 2 certified. Cloud services handle authentication, billing and aggregate reporting. Raw code and sessions are processed by the optional local CLI; an optional Relay shares only configured aggregate usage.
Do you offer volume discounts?
Contact matt@getburnrate.io to discuss organizational requirements and any available commercial terms. Custom pricing, integrations, SSO or an SLA are not included in the published cloud plans.
Put all your AI spend in one place
Explore the dashboard immediately, then connect a reporting account when you are ready. No credit card required.
See my AI spend freeProvider-reported cost · Encrypted credentials · Optional local CLI