| What it does | Test LLMs on your own tasks before you switch models
| See what every AI prompt costs and rewrite it in one click
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| GB
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | Standard: $99 one-time for 2 machines, including 1 year of updates. Pro coming soon.
| Free: $0 forever with 5 cloud optimizations per day, unlimited local rewrites, 100-prompt history with CSV export. Pro: $4.99/month or $39.99/year (save 33%) with 1,000 cloud optimizations per month, 500-prompt history with JSON export, Gemini 3 Flash Preview, custom focus presets, side panel worksp
|
|---|
| Key features | - Benchmark any OpenRouter model on your own prompts, CSVs or Hugging Face datasets
- Rubric-based scoring by AI judge, by hand, or both
- Cost per answered task with retries and caching
- Time to first token and output tokens per second per call
- Shareable reports in HTML, CSV and JSON formats
- Compare up to three past benchmarks side by side
- Hard spending cap per run
- Fully self-hosted on your machine
- No SDK or code changes required
| - Live token cost estimates across ChatGPT, Claude, Perplexity, Gemini, Grok, Poe, OpenRouter, ChatHub, TypingMind and You.com
- Side-by-side comparison of original vs optimized prompts with savings shown in tokens and credits
- Dashboard with savings statistics: today, 7-day, and total saved tracking
- Prompt history with export: 100-prompt history with CSV or JSON export
- Keyboard shortcuts (Alt+Shift+O) for hands-free optimization
- Privacy-first: prompts stay local unless you click Optimize
- Optional API monitoring to track spending across all AI tools you use
- Transparent cost calculation using official per-token rates from each AI provider
|
|---|
| What makes it different | - Tests your own tasks with real data instead of generic benchmarks
- Comes before integration with no SDK or code changes needed
- Reports actual cost per answered task including retries and caching
- Entirely self-hosted with data never leaving your machine
- One shareable report with every answer and judge reasoning
| - No setup, API key, or third-party trackers required
- Transparent methodology with published formulas and per-model rates anyone can verify
- Works across 10 major AI platforms with a single extension
- Privacy by default: prompts never logged or stored
- Intentionally pessimistic estimates prevent bill surprises
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 0 |
|---|
| Citation Flow (Majestic) | 16 | 10 |
|---|
| Referring domains (Majestic) | 3 | 2 |
|---|
orbench
Token Wise