I Escondido·In 7 weeks (June 2026)
ForaCity Developer Portal

Cost Calculator

Estimate AI processing, data, and infrastructure costs at any scale — with live platform data

Loading Live Platform Data...

Projected Scale

$677
Monthly Cost
$8.1K
Annual Cost
$35.64
Per Jurisdiction/mo
$0.17
Per Active User/mo

Scale at County

19
Total Jurisdictions
18
Cities
1
Counties
260
Officers Served
4.1K
Monthly Users
1
Servers
AI / LLM Processing
84.7%$573.80/mo

Meeting summaries, conflict checks, proposal analysis, chat, research synthesis, sentiment analysis

External APIs
6.1%$41.00/mo

ArcGIS geocoding, NetFile sync, CivicPlus agendas (most are free)

Compute (Servers)
5.0%$33.87/mo

1 server(s) running tRPC API, subdomain routing, background jobs

CDN / Bandwidth
2.0%$13.43/mo

Content delivery, static assets, API responses to end users

Database (TiDB)
1.8%$12.25/mo

Storage + request units for all jurisdiction data, officers, contributions, proceedings

File Storage (S3)
0.4%$2.58/mo

Documents, images, meeting recordings, Form 700 PDFs, proposal attachments

Search Index
0.0%$0.19/mo

Full-text search across officers, legislation, meetings, proposals

Revenue vs. Cost Analysis

ScaleJurisdictionsMonthly CostAvg ContractMonthly RevenueGross Margin
Single City1$68$2.3K/mo$2.3K97%
County19$677$2.1K/mo$20.8K97%
State (CA)540$19.9K$2.2K/mo$178.0K89%
Region (5 States)2.8K$98.0K$2.1K/mo$590.2K83%
National (50 States)22.6K$799.5K$2.1K/mo$2.4M67%
Revenue assumes blended contract values ($10K–$70K/yr) with conservative market penetration (5–50% depending on scale). Actual margins will vary based on pricing strategy, customer mix, and usage patterns.

AI Processing Cost Detail

AI FunctionCost/CallEst. Calls/moMonthly Cost
Meeting Summaries$0.12136$16.32
Conflict Checks$0.041.0K$40.40
Proposal Analysis$0.35260$91.00
Chat Messages$0.0215.8K$316.00
Research Synthesis$0.50165$82.50
Sentiment Analysis$0.03690$20.70
Budget Analysis$0.0886$6.88

Scale Comparison — All Tiers

Assumptions & Methodology

City Size Tiers

  • Small <50K population — 4 meetings/mo, 5 officers, 50 MAU
  • Medium 50K–200K — 8 meetings/mo, 15 officers, 200 MAU
  • Large 200K+ — 16 meetings/mo, 40 officers, 800 MAU

LLM Pricing

Based on GPT-4o-class models at current API pricing. Costs decrease ~30% annually as models improve and competition increases. Batch processing and caching can reduce costs by 40–60%.

Live Data

The Live Platform Data panel queries all 96 database tables in real-time to show actual entity counts, AI invocation estimates, and storage usage. AI costs are derived from entity counts multiplied by per-call pricing.

Infrastructure

TiDB Serverless (auto-scaling MySQL), S3 for file storage, CDN for static assets. Compute based on t3.medium equivalent at ~$34/mo. One server per ~500 jurisdictions.

Cost Optimization Strategies

  • • LLM response caching for repeated queries (est. 40% savings)
  • • Batch processing for non-real-time analysis (est. 30% savings)
  • • Smaller models for simple tasks (sentiment, classification)
  • • Reserved capacity pricing at scale (est. 20% savings)
  • • Edge caching for static compliance data