Tokensaver, see which parts of your LLM prompt cost money

A new open-source tool called tokensaver reports that it cut a sample customer-support system prompt from 834 to 665 tokens on gpt-4o, a 20.3% reduction worth $0.4225 per 1,000 calls and $422.50 per 1 million calls. tokensaver runs fully offline, counts tokens and compares costs across major AI models, and attaches a reason, token savings and dollar value to each suggestion; its default safe rules alone drop the same prompt from 834 to 772 tokens, with review suggestions worth 107 more tokens. The tool's token counting, cost comparison, JSON minification, whitespace cleanup and duplicate detection are tested in CI on 55 languages, though its filler-phrase rule currently covers only English.

Find out what your prompt costs on every major AI model, and exactly which changes make it cheaper. Most token counters stop at a number. tokensaver tells you what to change : every suggestion comes with a reason, the tokens it saves, and what that is worth in dollars. It runs 100% offline. Your prompt never leaves your machine. tokensaver works with prompts in any language and any script. Token counting, cost comparison, JSON minification, whitespace cleanup and duplicate detection are tested in CI on 55 languages on every commit see the test https://github.com/behrouzbk/tokensaver/blob/main/tests/test languages.py : Arabic · Bengali · Bulgarian · Burmese Myanmar · Chinese Simplified · Chinese Traditional, Hong Kong · Chinese Traditional, Macau · Chinese Traditional, Taiwan · Croatian · Czech · Danish · Dutch · English · Estonian · Finnish · French · German · Greek · Hebrew · Hindi · Hungarian · Indonesian · Italian · Japanese · Kannada · Khmer · Korean · Lithuanian · Malay · Malayalam · Marathi · Nepali · Nigerian Pidgin · Norwegian · Persian Farsi · Polish · Portuguese Brazil · Portuguese Portugal · Punjabi Gurmukhi · Romanian · Russian · Serbian Cyrillic · Slovak · Slovenian · Spanish · Swahili · Swedish · Tagalog Filipino · Tamil · Telugu · Thai · Turkish · Ukrainian · Urdu · Vietnamese Right-to-left scripts Arabic, Hebrew, Persian, Urdu and languages without spaces between words Chinese, Japanese, Thai, Khmer, Burmese included. The filler rule still speaks only English. Native speakers: add your language's filler phrases in 5 https://github.com/behrouzbk/tokensaver/issues/5 . examples/messy prompt.txt is a typical customer-support system prompt: polite filler, a rule written twice, a paragraph pasted twice, and pretty-printed JSON. bash $ tokensaver optimize examples/messy prompt.txt --apply all Suggestion Tokens $/1k calls Status 1 Minify JSON block 140 chars, was 185 line 13 -18 $0.0450 applied 2 Minify JSON block 200 chars, was 392 line 39 -43 $0.1075 applied 3 Duplicate line: “- Never share internal information…” line 30 -12 $0.0300 applied 4 Duplicate paragraph: “Please note that you must only…” line 34 -41 $0.1025 applied 5 Repeated instruction: “Make sure you keep the answer…” line 32 -12 $0.0300 applied 7 Filler: “I would like you to…” ×1 line 4 -6 $0.0150 applied ... 15 Long example ~198 tokens line 60 ≤198 $0.4950 flag ╭──────────────────────── Total savings on gpt-4o ─────────────────────────╮ │ Before: 834 tokens │ │ After: 665 tokens │ │ Saved: 169 tokens 20.3% = $0.000423 per call, $0.4225 per 1,000 calls, │ │ $422.50 per 1M calls │ ╰──────────────────────────────────────────────────────────────────────────╯ What changed in the prompt: -I would like you to please read the customer's message carefully and answer their question. -As an AI language model, you should always be polite, friendly and professional. +Read the customer's message carefully and answer their question. +You should always be polite, friendly and professional. ... -{ - "answer": "string", - "category": "billing | technical | account | other", - ... -} +{"answer":"string","category":"billing | technical | account | other","confidence":0.0,...} ... -- Never share internal information, discount codes or employee names. -- Make sure you keep the answer under 120 words. With only the default safe rules no wording changes at all , the same prompt drops from 834 to 772 tokens. tokensaver then tells you that the review suggestions would save 107 more, so you decide. pip install prompt-tokensaver The command is tokensaver . Requires Python 3.10 or newer. Works on Windows, macOS and Linux. 1. How many tokens, and what does one call cost? tokensaver count prompt.txt --model gpt-4o tokensaver count "Summarize this article in three bullet points." 2. Which model is cheapest for this prompt? tokensaver compare prompt.txt tokensaver compare prompt.txt --models gpt-4o,claude-sonnet-5-5,gemini-2.5-flash 3. What should I change? safe changes are applied, others are suggested tokensaver optimize prompt.txt 4. Apply everything you agree with and save a copy the original is never overwritten tokensaver optimize prompt.txt --apply all --output prompt.optimized.txt tokensaver optimize prompt.txt --apply json,whitespace,filler -o prompt.optimized.txt Pipe text in with "-", list models and prices cat prompt.txt | tokensaver count - PowerShell: Get-Content prompt.txt | tokensaver count - tokensaver models Windows paths work as usual: tokensaver optimize examples\messy prompt.txt . Run tokensaver <command --help for the same information in your terminal. INPUT can be any of: | You pass | tokensaver reads | |---|---| | prompt.txt or C:\prompts\system.md | the file UTF-8; a byte-order mark is ignored | | - | text piped in on stdin | | "Summarize this in 3 bullets." | the text itself | A mistyped file name like promt.txt is an error, not silently counted as text. Token count and input cost on one model. | Option | What it does | |---|---| | --model , -m | Model to price against. Default: gpt-4o . See tokensaver models for all names. | | --prices FILE | Use your own prices.json instead of the bundled one. | Tokens and input cost on many models, cheapest first. | Option | What it does | |---|---| | --models a,b,c | Only these models comma-separated . Default: all of them. | | --prices FILE | Use your own prices.json . | Suggestions with the tokens and dollars each one saves, a before/after diff and the total. | Option | What it does | |---|---| | --model , -m | Model to measure savings on. Default: gpt-4o . | | --apply safe | Default. Applies only the safe rules json , whitespace . Review rules are listed with their savings but not applied. | | --apply all | Applies every rule. Read the suggestions first. | | --apply none | Applies nothing; just shows the suggestions. | | --apply json,duplicates | Applies only the rules you list. Names: json , whitespace , duplicates , repeated-instructions , filler , long-examples . | | --output FILE , -o FILE | Saves the optimized prompt to FILE . Without it, nothing is written. The input file is never overwritten. | | --force | Lets --output replace a file that already exists. It still refuses to overwrite the input file. | | --no-diff | Hides the before/after diff it is shown by default . | | --prices FILE | Use your own prices.json . | Common combinations: tokensaver optimize prompt.txt look first: safe fixes only, nothing saved tokensaver optimize prompt.txt --apply all -o prompt.min.txt apply everything, save a copy tokensaver optimize prompt.txt --apply json,whitespace,duplicates -o prompt.min.txt tokensaver optimize prompt.txt -m claude-sonnet-5-5 --no-diff savings on Claude, short output tokensaver optimize prompt.txt --apply all -o prompt.min.txt --force re-run and replace the copy models lists every supported model with its prices and whether counts are exact. version prints the installed version. Each rule is a small module in src/tokensaver/optimizer/ https://github.com/behrouzbk/tokensaver/tree/main/src/tokensaver/optimizer . Safe rules cannot change meaning and are applied by default. Review rules are shown with their savings and applied only when you ask --apply all or --apply <rule,... . Code blocks are never changed. Few-shot examples are never reworded. | Rule | Risk | What it does | |---|---|---| | json | safe | Minifies pretty-printed JSON. Only whitespace outside strings is removed; the result is re-parsed and compared, so keys, values and number formats stay exactly the same. | | whitespace | safe | Removes trailing spaces, extra blank lines and blank lines at the start and end. Indentation and spaces inside lines are kept. | | duplicates | review | Finds duplicate lines and duplicate or near-duplicate ≥90% similar paragraphs. | | repeated-instructions | review | Finds the same instruction given twice in different words, such as "Always respond in JSON" and "Remember to always respond in JSON". | | filler | review | Removes polite filler "I would like you to please…", "As an AI language model…", "Thanks in advance " and shortens wordy phrases "in order to" → "to" . | | long-examples | review | Flags few-shot examples over ~150 tokens and prompts with more than 3 examples. Only flags them; it never edits. | Every saving is measured : tokensaver counts the prompt before and after each change on the model you chose. Changes that save nothing on that model are not listed. Safe whitespace fixes that save 0 tokens are still applied for a tidy file, and reported in one line. Prices are USD per 1M tokens, standard tier, as of 2026-10-26 . They live in src/tokensaver/data/prices.json https://github.com/behrouzbk/tokensaver/blob/main/src/tokensaver/data/prices.json with a source URL for each model. Edit that file, or pass your own with --prices my prices.json . | Model | Provider | Input / 1M | Output / 1M | Token count | |---|---|---|---|---| | gpt-6-astra | OpenAI | $10.00 | $50.00 | estimated | | gpt-6.1-sol | OpenAI | $2.00 | $10.00 | estimated | | gpt-6-luna | OpenAI | $0.10 | $0.50 | estimated | | gpt-5.5 | OpenAI | $5.00 | $30.00 | exact | | gpt-5.4-mini | OpenAI | $0.75 | $4.50 | exact | | gpt-5-mini | OpenAI | $0.25 | $2.00 | exact | | gpt-4.1 | OpenAI | $2.00 | $8.00 | exact | | gpt-4.1-mini | OpenAI | $0.40 | $1.60 | exact | | gpt-4o | OpenAI | $2.50 | $10.00 | exact | | gpt-4o-mini | OpenAI | $0.15 | $0.60 | exact | | claude-fable-5-1 | Anthropic | $10.00 | $50.00 | estimated | | claude-opus-5-5 | Anthropic | $4.00 | $20.00 | estimated | | claude-sonnet-5-5 | Anthropic | $2.00 | $10.00 | estimated | | claude-haiku-5-5 | Anthropic | $0.10 | $0.50 | estimated | | claude-haiku-4-5 | Anthropic | $1.00 | $5.00 | estimated | | gemini-4-argon | | $2.00 | $10.00 | estimated | | gemini-3.8-flash | | $0.75 | $3.75 | estimated | | gemini-3.1-pro-preview | | $2.00 | $12.00 | estimated | | gemini-2.5-flash | | $0.30 | $2.50 | estimated | | gemini-2.5-flash-lite | | $0.10 | $0.40 | estimated | Run tokensaver models to see the list for your installed version. Please read this before relying on the numbers. - Exact vs estimated. Counts are exact only for OpenAI models that tiktoken maps to a tokenizer shown as "exact" . Claude, Gemini and GPT-6 have no offline tokenizer, so tokensaver counts with OpenAI's o200k base and multiplies by a per-model factor from prices.json . These are always shown with ~ and labelled "estimated". The factors are rough heuristics, not measurements; real counts can differ by 10–20% or more, especially for code and non-English text. For exact counts, use the provider's own token-counting API. - Input cost only. count , compare and optimize price the prompt you send. Output tokens, cached-input discounts, batch discounts and long-context surcharges for example above 200K tokens on Gemini 3.1 Pro or 100K on Claude Haiku 5.5 are not included. - Prices go stale. Check the last updated date in the output. Some listed prices are scheduled to change see the notes field in prices.json . - Languages. Token counting and the json , whitespace and duplicates rules work in every language tested on 55, see above . The filler and repeated-instructions rules, and "Example 1:" detection, currently understand English only. Estimates for Claude and Gemini are less reliable for non-English text. - Message overhead is not counted. Chat APIs add a few tokens per message for roles and formatting. tokensaver counts the text you give it. - Rules are heuristics. Review suggestions can be wrong: a repeated sentence can be intentional emphasis, and "duplicate" lines can be real data. That is why they are never applied unless you ask. - Offline by design. tokensaver makes no network calls. The tokenizer files ship inside the package and are checked against their published SHA-256 hashes. - Calibrate the Claude and Gemini estimate factors against official token counters - --json output for CI pipelines and scripts - Output-token and prompt-caching cost estimates - Directory mode: scan all prompts in a project - More rules: verbose markdown, long URLs, unused template variables - GitHub Action that comments token savings on pull requests Ideas and votes are welcome in the issues. ⭐ If tokensaver saved you tokens, a star helps other developers find it. Contributions are very welcome: new rules, better heuristics, price updates and bug reports. Read CONTRIBUTING.md https://github.com/behrouzbk/tokensaver/blob/main/CONTRIBUTING.md for the 5-minute setup. Each rule is one small file with its own tests, so it is a good first contribution. tokensaver catches the easy wins. If your AI bill is growing and you want a deeper review of prompts, model choice, caching and architecture, I can help. 👉 Get in touch https://axieo.ca or email info@axieo.ca mailto:info@axieo.ca ☕ tokensaver is free and MIT licensed. If it saves you money, you can buy me a coffee https://buymeacoffee.com/jiq8aoqxeo .