reTOONer.com

Cut your token
bill by half.

11 free tools that compress prompts, strip code bloat, split agent contexts, and show you exactly where your tokens burn. Works with OpenAI, Claude, Ollama, LM Studio, and any LLM. Everything runs in your browser.

11tools
30-60%savings
0data sent
01
Converter
JSON → TOON

Strip brackets, quotes, and punctuation noise from JSON configs. Keep structure intact. Paste into prompts at a fraction of the token cost.

JSON Input0 tok
TOON Output0 tok
JSON: 0 chars, 0 tokTOON: 0 chars, 0 tokSaved: 0%
02
Converter
TOON → JSON

Reverse conversion. Reconstruct valid JSON from compact TOON notation.

TOON Input0 tok
JSON Output0 tok
TOON: 0 chars, 0 tokJSON: 0 chars, 0 tok
03
Converter
YAML → TOON

Many agent frameworks use YAML configs. Strip the dashes and quotes for lighter prompts.

YAML Input0 tok
TOON Output0 tok
YAML: 0 chars, 0 tokTOON: 0 chars, 0 tokSaved: 0%
04
Optimizer
Prompt Minifier

Strip filler words, verbose phrasing, and over-polite bloat from system prompts. Same meaning, way fewer tokens.

Original0 tok
Minified0 tok
Before: 0 chars, 0 tokAfter: 0 chars, 0 tokSaved: 0%
05
Analysis
Token Cost Calculator

See exactly what your prompts cost across 12 models. Daily, monthly, yearly — plus estimated savings after optimization.

Input

Cost Breakdown

Input tokens-
Output tokens-
Cost / call-
Daily-
Monthly-
Yearly-

After reTOONer (-40%)

Optimized tokens-
Monthly savings-
Yearly savings-
06
Analysis
Token Heatmap

Color-coded visualization of token density. See which words and sections are eating your budget.

Prompt0 tok
Heatmap
Paste a prompt and click Analyze...
LowMedHigh
Total: 0 tokWorst: -Avg: - tok/word
07
Comparison
Prompt Diff

Compare two prompt versions side by side. See exactly what changed and how it affects token count.

Version A0 tok
Version B0 tok
A: 0 tokB: 0 tokDelta: 0
08
Optimizer

Code Compressor — Shrink Code for LLM Context

Paste Python, JS, or any code. Strip comments, docstrings, type hints, blank lines. Built for Ollama, LM Studio, and local models.

Code Input0 tok
Compressed0 tok
Before: 0 chars, 0 tokAfter: 0 chars, 0 tokSaved: 0%
09
Planning

Context Window Budget Planner

Allocate your context window. Essential for Ollama, LM Studio, llama.cpp with 4K-32K limits.

20%
15%
25%
15%
25%
10
Tuning

Sampling Config Optimizer

Recommended temperature, top_p, top_k, repeat_penalty. Works with Ollama, LM Studio, llama.cpp, vLLM.

Use Case

Recommended Config

Select a task type...
11
Workflow

Context Splitter — Minimal Payloads for Agent Calls

Paste your full agent context (agent.md, soul, memory, instructions). Tag each section as Always Send, Review Only, or Skip. Generate minimal payloads for cheap model calls and full payloads for flagship review. Built for the sub-agent workflow — cheap models build, flagships review.

Full Agent Context0 tok
Copied!