No GitHub data — configure .env
202 tests 0 open PRs

FinOps Dashboard

Real costs for the Raku platform. All numbers USD/month.

Total Monthly Burn
$0.01
3 of 4 services at $0 (free tier)

Cost Breakdown

OpenAI Embeddings

Estimate
$0.01

text-embedding-3-small @ $0.02/1M tokens. ~5 tenants × 100 memories × 500 tokens = 250K tokens/mo

Embeddings are the #1 variable cost per Ware. text-embedding-3-small at $0.02/1M tokens. At 1000 memories per tenant per month = $0.01/tenant.

Fly.io Compute

Actual
$0.00

Hobby plan: shared-cpu-1x, 256MB RAM, 1GB encrypted volume. Free allowance covers current usage

Fixed cost shared across all tenants. At 100 tenants = $0/tenant (hobby). At scale: $5.70/mo (dedicated-cpu-1x) / 100 tenants = $0.06/tenant.

GitHub Actions CI/CD

Estimate
$0.00

Free tier: 2,000 min/mo (Pro: 3,000). Each CI run ~3-5 min. ~30 pushes/mo = ~120 min

CI cost scales with push frequency. Each CI run ~4 minutes × 30 pushes/mo = 120 min/mo. Well within free tier (2,000 min). Overage: $0.008/min.

Cloudflare

Actual
$0.00

Free tier: Pages, DNS, SSL, email routing, R2 (10GB free). Zero cost at current scale

CDN, DNS, SSL, email routing all free. Scales to millions of requests before paid tier kicks in.

Portkey AI Gateway

Coming Soon
$0.00

Coming June. Free tier: 10K requests/mo. Will track per-tenant tokens and model costs

LLM calls are the #2 variable cost. Cortex routing to cheapest capable model is the margin strategy.

Unit Economics Calculator

10
1 100 200 300 400 500
LLM Usage Pattern
COGS/Ware
$2.01
Target: $13-33
Revenue/Ware
$199.00
/month
Gross Margin
99.0%
Target: 84-94%
Monthly Profit
$2.0K
$23.9K ARR
COGS: $20.10 Revenue: $2.0K
99% margin
Breakeven
Profitable
Path to $1M ARR
~419 Wares
Current ARR Run Rate
$23.9K

Cortex Tier Pricing Model

Cortex routes each request to the cheapest capable model. Tier 0-1 are free (cached/rule-based). This is the margin strategy.

Tier Name Model Input $/1M Output $/1M Latency
0 Cache Hit None (cached) Free Free ~1ms
1 Pattern Match None (regex/rules) Free Free ~5ms
2 Embedding Only text-embedding-3-small $0.02 Free ~50ms
3 Fast LLM Claude Haiku 4.5 $1.00 $5.00 ~200ms
4 Balanced LLM Claude Sonnet 4.6 $3.00 $15.00 ~1-2s
5 Deep Reasoning Claude Opus 4.6 $15.00 $75.00 ~3-8s
6 Custom Pipeline Multi-model chain Free Free Variable

Portkey AI Gateway integration coming June. Will enable real per-tenant token tracking and automatic tier selection.

All costs are estimates based on published pricing. Live tracking via Portkey coming June 2026.