HN Showcase
Back to browse
Vibe-budget – CLI to estimate LLM costs before you start vibe coding

Vibe-budget – CLI to estimate LLM costs before you start vibe coding

by gabriel_quec016·Mar 14, 2026·4 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemCozy

Task detection from plain English beats manual token calculators for AI coding budgets.

Strengths
  • •Detects technical tasks from natural language without requiring API keys.
  • •Compares real-time pricing across 85+ models side by side.
  • •Scan command estimates refactoring costs for existing codebases.
Weaknesses
  • •Token estimates are heuristic-based, not grounded in actual model behavior.
  • •OpenRouter dependency means pricing accuracy tied to their API.
Target Audience

Developers using AI coding assistants

Similar To

OpenRouter Pricing Page · Tokenizer tools · LLM cost calculators

Post Description

I built vibe-budget because I kept burning tokens without knowing the cost upfront. You describe your project in plain English (or Spanish), and it detects the tasks involved, estimates token usage, and compares real-time prices across 85+ models via OpenRouter.

Example: vibe-budget plan ecommerce with stripe oauth and supabase

It detects 4 tasks, estimates ~497k tokens, and shows you the cheapest, best quality-price, and premium model options side by side.

It also has a scan command — point it at an existing codebase and it estimates how many tokens it would cost to refactor or extend it with AI.

No API key required. Prices are fetched live from OpenRouter with a 1-hour cache fallback.

npm install -g vibe-budget

Docs: https://gaboexe0.github.io/vibe-budget/ Repo: https://github.com/gaboexe0/vibe-budget

Similar Projects