Oliver/ai-cost-tracker
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
No description
19 commits 1 branch 0 tags 140 KiB
Find a file
Vadym Samoilenko dfa32a91c7 feat: add google_tts generic model pricing + video-accessibility backfill script 
- Add google_tts/google_tts entry to models.yaml (16 USD/1M chars, WaveNet tier)
- Add scripts/migrate_video_accessibility.py for historical data backfill:
  migrates 25 users and 103 jobs (Gemini + TTS usage records) from
  accessible_video MongoDB into cost tracker

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-27 14:59:42 +01:00
.claude feat: dev login + optical-dev deploy setup 2026-04-27 12:05:42 +01:00
backend feat: add google_tts generic model pricing + video-accessibility backfill script 2026-04-27 14:59:42 +01:00
frontend fix: show 6 decimal places for small costs (< $0.01) 2026-04-27 14:36:15 +01:00
infra feat: add server-side update.sh script for in-place deploys 2026-04-27 12:30:50 +01:00
scripts feat: add google_tts generic model pricing + video-accessibility backfill script 2026-04-27 14:59:42 +01:00
sdk feat: initial implementation of Oliver AI Cost Tracker 2026-04-27 11:26:08 +01:00
.env.example feat: dev login + optical-dev deploy setup 2026-04-27 12:05:42 +01:00
.gitignore feat: initial implementation of Oliver AI Cost Tracker 2026-04-27 11:26:08 +01:00
README.md fix: remove readme field from pyproject.toml, add README.md 2026-04-27 12:20:50 +01:00

README.md

AI Cost Tracker

Shared AI cost tracking service for Oliver Agency projects.

Tracks LLM usage costs across workspaces, teams, and projects. Provides a REST API for recording AI calls and an admin dashboard for analytics.

Stack

  • Backend: FastAPI, MongoDB, Redis, Celery
  • Frontend: React, Vite, TypeScript
  • Auth: Azure AD SSO (+ dev login for local testing)
  • Deploy: Docker Compose on optical-dev

Quick start

cp .env.example .env
# Fill in Azure AD credentials and secrets
docker compose -f infra/docker-compose.yml up -d

Admin UI: http://localhost:5174 API docs: http://localhost:8001/docs