FlipPrice
An open-source pricing assistance tool for vintage resellers. Based on photos and field inputs, it generates listing drafts, fair price ranges, and net income estimates, using local inference with open-source weights models.
Timeline (last 90 days)
FlipPrice is an open-source project under the MIT license, positioned as a "side-hustle pricing copilot," with its code hosted on GitHub (https://github.com/firfircelik/flipprice).
FlipPrice's inputs include product photos as well as fields such as name, brand, category, condition, era, and purchase cost, and its output is divided into three parts: a listing draft, a fair price range, and the net amount received.
FlipPrice's listing draft is generated by a local open-source-weights model, with the title starting with the brand.
FlipPrice has been verified on Apple M2 with Python 3.14, and the installation process is to clone the repository, create a venv, pip install, ollama pull gemma3:1b, start uvicorn, and it also provides a one-click Render deployment button.
FlipPrice's description generation uses Gemma 3 (via Ollama) and has a local fallback chain to support offline operation.
FlipPrice's pricing engine uses TabPFN first, with Ridge regression as a fallback.
The author once tried RandomForest as the pricing model, but it exhibited a monotonicity failure on a small 20-row sample CSV, so it was abandoned.
The FlipPrice repository has 7 tests all passing, organized by user journey, covering the marketplace flow, offline mode, malicious input, photo attachments, and live model tests.
The author used a "simulated seller" persona for self-testing, and the results of real-time valuation of three items with Gemma 3 were: Canon AE-1 bought for 60, p50 estimate 286.34, net proceeds 189.12; Levis 501 bought for 15, p50 108.85, net proceeds 79.70; Sony WH-1000XM3 bought for 40, p50 116.82, net proceeds 61.63.
FlipPrice currently has no external real users, and the next step is to find actual resellers to test with.
1 more timeline events
All Facts (11)
FlipPrice is an open-source project under the MIT license, positioned as a "side-hustle pricing copilot," with its code hosted on GitHub (https://github.com/firfircelik/flipprice).
50%UnverifiedFlipPrice's inputs include product photos as well as fields such as name, brand, category, condition, era, and purchase cost, and its output is divided into three parts: a listing draft, a fair price range, and the net amount received.
50%UnverifiedFlipPrice's listing draft is generated by a local open-source-weights model, with the title starting with the brand.
50%UnverifiedFlipPrice has been verified on Apple M2 with Python 3.14, and the installation process is to clone the repository, create a venv, pip install, ollama pull gemma3:1b, start uvicorn, and it also provides a one-click Render deployment button.
50%UnverifiedFlipPrice's description generation uses Gemma 3 (via Ollama) and has a local fallback chain to support offline operation.
50%UnverifiedFlipPrice's pricing engine uses TabPFN first, with Ridge regression as a fallback.
50%UnverifiedThe author once tried RandomForest as the pricing model, but it exhibited a monotonicity failure on a small 20-row sample CSV, so it was abandoned.
50%UnverifiedThe FlipPrice repository has 7 tests all passing, organized by user journey, covering the marketplace flow, offline mode, malicious input, photo attachments, and live model tests.
50%UnverifiedThe author used a "simulated seller" persona for self-testing, and the results of real-time valuation of three items with Gemma 3 were: Canon AE-1 bought for 60, p50 estimate 286.34, net proceeds 189.12; Levis 501 bought for 15, p50 108.85, net proceeds 79.70; Sony WH-1000XM3 bought for 40, p50 116.82, net proceeds 61.63.
50%UnverifiedFlipPrice currently has no external real users, and the next step is to find actual resellers to test with.
50%UnverifiedThe Gemma 3 1B small model used by default in FlipPrice has limited generation quality, TabPFN's paid threshold is a breaking point for purely free users, and the lack of real user data makes valuation accuracy questionable.
50%