AI tools
Workflow
Before you paste (privacy, cleanup, splitting)
- PII RedactorReplace emails, phones, card numbers, IBANs, API keys and national ID numbers from 18 countries with placeholders before using an LLM, then restore them in its answer. Runs in your browser.
- API Key and Secret ScannerFind API keys, tokens, private keys and passwords in text before you paste it into ChatGPT or Claude, then copy a redacted version. Runs in your browser.
- Remove EXIF Data from PhotosRemove EXIF, GPS location, XMP and other metadata from JPEG, PNG and WebP photos without re-compressing them. Batch files, ZIP download, no upload.
- AI Text CleanerClean text from ChatGPT, Claude or Gemini: remove hidden characters, straighten curly quotes, handle em dashes, strip Markdown symbols and tidy spaces and blank lines.
- RAG Chunk CalculatorEnter document length, chunk size and overlap to get the number of chunks, repeated tokens and total embedding tokens. Paste text to preview the chunk boundaries.
- Text Splitter for LLMSplit a long text into parts that each fit a token limit, cutting at paragraph and sentence ends. Optional Part 1/N headers, copy each part, download TXT or ZIP.
Cost and limits
- Token CounterOpenAI and ChatGPT token counter (exact o200k_base, cl100k_base) with Claude and Gemini estimates. Paste text to count tokens; nothing leaves your browser.
- LLM API Cost CalculatorClaude, OpenAI (GPT) and Gemini API pricing in one calculator: enter tokens per request and requests per day to get daily and monthly API cost.
- LLM Batch Cost EstimatorLoad a CSV, fill in a prompt template and see the total LLM API cost of running every row, with prompt cache and Batch API savings. Runs in your browser.
- Context Window CalculatorSee what percent of each model's context window your text fills, how many tokens are left, and roughly how many words and pages. Sizes from official docs.
- Prompt Caching CalculatorSee how much prompt caching saves on repeated LLM calls. Cache write and read prices for Claude (5 minute and 1 hour), OpenAI and Gemini, with the break-even call count.
- LLM Rate Limit CalculatorTurn RPM, input and output TPM and RPD limits into requests per minute, the limit that binds, total job time and the concurrency you need. Claude tier presets included.
- Chat Conversation Cost CalculatorA chat API resends the whole history every turn. See cumulative tokens and cost over a conversation, the saving from prompt caching and the turn where the context window runs out.
- Fine-Tuning Cost CalculatorEstimate the cost of fine-tuning an OpenAI model from training tokens and epochs, then compare monthly inference on the fine-tuned model with the base model.
- Embedding Storage CalculatorEstimate how many vectors your documents make after chunking with overlap, how much storage they need at float32, float16, int8 or binary, and what the embeddings cost.
- Image Token CalculatorCount the input tokens an image uses in GPT, Claude and Gemini from its width and height, then see the cost for any number of images. Official resize rules.
- Audio Transcription Cost CalculatorEnter the audio length and compare speech to text costs for Whisper, gpt-4o-transcribe, gpt-transcribe and Gemini audio tokens.
Checking results
- LLM JSON Output ValidatorPaste an LLM JSON response and its JSON Schema to see every error with its path and line. Code fences, trailing commas and wrong quotes are fixed first.
- AI Math CheckerPaste an AI answer and every calculation in it is recalculated. Wrong results are marked in red, with links to the matching calculator. Runs in your browser.
- Prompt Diff with Token CountCompare two versions of a prompt: word-level diff, tokens for each version, the difference and the input cost change per call and for any number of calls.
Running locally
- GPU VRAM Calculator for Local LLMsEstimate the VRAM a local LLM needs from parameters, quantization bits and context length. Shows weights, KV cache and overhead, and which GPU it fits.
- LLM Quantization Size CalculatorCompare GGUF file size and memory for F16, Q8_0, Q6_K, Q5_K_M, Q4_K_M, Q3_K_M and Q2_K from the parameter count, with KV cache for your context length.
- Tokens per Second CalculatorTurn output tokens, tokens per second and time to first token into response time, or find the speed you need.
Other
Browser tools that check the token, context window, cost and VRAM math AI often gets wrong, and help with everyday AI work.
LLM API pricing table (prices per 1M tokens, JSON and CSV download)