Overview
See the estimated cost and value of every AI conversation. Local ONNX classification; content stays in your browser.
Veritiana AI Meter helps you understand the real value of your AI usage in the browser. The extension measures visible conversations on supported AI platforms such as ChatGPT, Claude and Gemini. It estimates input tokens, output tokens, visible context size, API-equivalent cost, task type, complexity and classifier confidence. All classification runs locally in your browser using an embedded ONNX model. Raw prompts and AI responses are not uploaded to Veritiana servers. Veritiana AI Meter is useful if you want to understand: • how much AI usage you actually generate • what types of tasks you use AI for • whether your usage is mostly simple, medium or complex • how browser usage compares to subscription or API-equivalent value • how much visible AI activity is happening over time The extension adds a small local measurement badge under supported AI responses and provides a popup dashboard with recent measurements, estimated cost, task classification, complexity and monthly usage. Privacy-first design: • raw conversation content stays in the browser • local ONNX classification • local measurement history • optional metrics sync only • no raw prompts or AI responses are uploaded Supported platforms: • ChatGPT • Claude • Gemini Veritiana AI Meter does not provide exact billing data. All token counts and costs are estimates based on visible browser content and reference API-equivalent pricing.
0 out of 5No ratings
Details
- Version1.4.9 — functional anonymous dashboard; local ONNX; optional metrics sync
- UpdatedJuly 27, 2026
- Size2.86MiB
- LanguagesEnglish
- DeveloperWebsite
Email
signal@veritiana.com - Non-traderThis developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.
Privacy
This developer declares that your data is
- Not being sold to third parties, outside of the approved use cases
- Not being used or transferred for purposes that are unrelated to the item's core functionality
- Not being used or transferred to determine creditworthiness or for lending purposes