102 tools
Every tool
All free, all running entirely in your browser, none behind a sign-up. Prices come from 42 models tracked against their providers’ own documentation, and every token count states whether it is exact or estimated.
/
102 tools. Press / to search, or ⌘K from any page.
Counting 7
Measure what you are about to send, before you send it.
- LLM Token CounterReal BPE tokenization, not characters ÷ 4. Shows which counts are exact and which are estimates.
- Context Window CalculatorPaste your context. See which models swallow it whole and which will reject the request.
- Tokenizer PlaygroundEvery token rendered separately, with its ID. The fastest way to understand why a prompt is expensive.
- Words to Tokens ConverterQuick conversion in both directions, with separate ratios per content type instead of one wrong average.
- Token HeatmapLine-by-line token bars with a density flag for the expensive parts.
- LLM Cost by Language ComparatorToken multipliers by language, priced. Your margin differs by market.
- Context Window Budget PlannerWindow allocation with a safety margin and the fixed overhead shown.
Cost 13
Turn token counts into the number that appears on an invoice.
- LLM API Cost CalculatorRequests per month in, dollars out. Input, cached input and output priced separately.
- Chatbot Conversation Cost CalculatorHistory is resent every turn, so cost grows quadratically. Most budgets miss this entirely.
- LLM Model FinderSet a budget and a context requirement, get the shortlist. Sorted by your own input-to-output ratio.
- API Rate Limit CalculatorConvert traffic into TPM and RPM, and find the ceiling before production does.
- Agent Loop Cost SimulatorPer-iteration breakdown showing why agents cost several times the naive estimate.
- Subagent Token Budget PlannerBudget allocation across subagents, with fixed overhead subtracted first.
- Tokens per Dollar CalculatorBudget in, tokens and pages out. Makes abstract rates concrete.
- Batch API Savings CalculatorThe 50% discount most teams never claim, priced at your volume.
- Fine-Tuning Cost and Payback EstimatorTraining cost against the prompt tokens it removes, with payback in months.
- AI Cost per User CalculatorPer-user cost with the heavy-user tail modelled, and margin against your price.
- Reasoning Token Cost EstimatorHidden thinking tokens, billed as output. Budgets miss them entirely.
- Model Routing Savings CalculatorTwo-tier routing with escalation cost, and the break-even escalation rate.
- Annual LLM Budget PlannerWorkload breakdown plus twelve-month projection with growth compounding.
Optimisation 5
Remove what you are paying for and getting nothing back.
- Prompt Token OptimizerCuts whitespace, minifies JSON, collapses blank lines. Shows tokens saved and the annual value.
- Text Splitter for RAG and EmbeddingsToken-accurate chunking with configurable overlap. Respects sentence and paragraph boundaries.
- Prompt Diff and Token ComparisonBefore and after, with the token delta priced. The missing half of every prompt rewrite.
- Data Format Token ComparisonSame records, five formats, five very different token counts. Usually 50–70% is recoverable.
- Prompt Cache Structure CheckerFinds cache-busting content and measures the prefix that survives it.
Prompts 10
Write, check and repair the text that drives everything else.
- AI Prompt GeneratorFour task types, each producing a finished prompt with format spec and constraints.
- Prompt LinterStructural review of a prompt: what is costing you money and what will fail.
- Prompt Whitespace CleanerTrailing spaces, stray tabs, triple blank lines. Invisible and billed.
- XML Tag Prompt WrapperSplit sections into tagged blocks. Eight tokens each, real accuracy gain.
- Prompt Delimiter and Tag CheckerUnclosed, mismatched and stray tags, with the position of each.
- Few-Shot Example FormatterPairs in, formatted examples out. Four formats, priced.
- Prompt Template FillerPreview a filled template, and catch the variable you forgot to pass.
- Prompt Template Variable ExtractorEvery placeholder in a template, with counts and a generated type.
- Stop Sequence TesterWhere the model stops, what survives, and what you paid for regardless.
- System Prompt to Skills SplitterSplits a system prompt into what belongs there and what belongs in a skill.
Building 14
Compose prompts, agents, tools and skills — and price them as you write.
- AI Agent GeneratorChoose the agent type and get a finished config, not an empty form. Four blueprints.
- AI Skill GeneratorThree skill shapes — review, generate, diagnose — each producing a complete file.
- Structured Prompt BuilderDeterministic, not AI-generated. Six sections, live token cost, copy as plain text or XML tags.
- System Prompt AnalyzerPer-section token breakdown and the yearly price of each paragraph you leave in.
- AI Agent Configuration BuilderPortable agent config with the one number frameworks never show you: overhead per request.
- AI Skill File BuilderFrontmatter validation, trigger-quality checks, and the token cost of what loads into context.
- Function Calling Tool Schema BuilderOne line per tool, valid schema out, with the per-request cost shown.
- Tool Schema ValidatorName rules, description quality, schema shape, and the size you pay for.
- Tool Description OptimizerRemoves preamble and padding from tool descriptions. Paid on every request.
- MCP Server Config BuilderOne line per server, valid mcpServers JSON out.
- Skill File Frontmatter ValidatorThe checks that decide whether a skill ever gets loaded.
- Multi-Agent Handoff Prompt BuilderStructured handoffs that stop agents repeating each other’s work.
- Function Call Message FormatterValid tool_use / tool_result blocks with matching ids, both providers.
- Agent Memory Compaction PromptCompaction prompt that preserves decisions and numbers, drops the rest.
RAG 10
Chunk, retrieve and pack context without paying for what you discard.
- Embedding Cost CalculatorIndex build, re-indexing and query embedding, priced separately.
- Vector Database Storage EstimatorStorage by dimensions and precision, with quantisation savings shown.
- RAG Retrieval Budget CalculatorWhat retrieved context costs per month, and the k comparison table.
- Document Token ProfilerSection-by-section token share, with a density flag for dense content.
- RAG Metadata Overhead CalculatorThe per-chunk metadata tax, multiplied by k and by your traffic.
- RAG Chunk Quality CheckerFlags chunks that start mid-clause, refer to nothing, or are pure pointers.
- RAG Context PackerScore-ordered packing into a fixed budget, with drop reasons reported.
- Reranker Cost EstimatorReranker fee against the generation tokens it saves. Often net positive.
- RAG Citation FormatterNumbered, inline or XML citation formats, with the cost difference.
- Chunk Overlap VisualizerShows the repeated text between chunks and the storage it costs.
Evaluation 9
Find out whether a change actually improved anything.
- LLM Evaluation Rubric BuilderWeighted criteria with score anchors and mandatory evidence quotes.
- LLM-as-Judge Prompt BuilderJudge prompts with the verbosity and position bias countermeasures built in.
- LLM Response ComparatorWord overlap, exclusive terms, and the numbers that differ between answers.
- RAG Grounding CheckerSentence-level grounding check. Unsupported numbers flagged first.
- Citation Extractor and ValidatorUncited claims, out-of-range indices, and unused retrieved sources.
- Evaluation Dataset BuilderCases with expected outputs and difficulty, exported three ways.
- Confusion Matrix CalculatorFull metrics from four counts, plus the base rate warning accuracy needs.
- Inter-Rater Agreement Calculator (Cohen's Kappa)Cohen's kappa with disagreement list. Below 0.6, fix the rubric first.
- Prompt A/B Test Significance CalculatorTwo-proportion z-test with confidence interval and required sample size.
Datasets 5
Prepare, validate and split data for fine-tuning and testing.
- JSONL Validator for Fine-Tuning DatasetsLine-numbered parse errors plus the structural checks uploads actually fail on.
- Dataset Deduplicator for Fine-TuningCatches duplicates that differ only in case, spacing or punctuation.
- Train and Validation Set SplitterSeeded shuffle and split. Same seed, same split, comparable evaluations.
- Chat Messages Array BuilderReadable conversation in, valid API payload out, in three formats.
- OpenAI to Anthropic Format ConverterPort a payload between providers. Handles the system prompt difference.
Format 11
Convert payloads into the cheapest shape the model reads just as well.
- JSON Formatter for PromptsFormat or minify, with the token cost of each shown side by side.
- JSON Minifier for LLM PayloadsOne-click minification with the token saving priced at your volume.
- JSON Validator with Token ReportParse errors with position, plus depth and the cost of your indentation.
- JSON String Escaper for PromptsEscape a prompt into a JSON field, or recover one from a request log.
- JSON to CSV for Cheaper PromptsRecords in, CSV out. Usually 50–70% fewer tokens than the JSON array.
- CSV to JSON ConverterSpreadsheet export in, clean JSON records out, with types inferred.
- Agent Config JSON to YAMLJSON agent definitions into the YAML that frameworks actually read.
- Agent Config YAML to JSONYAML config into API-ready JSON, with the token overhead measured.
- Markdown to Plain Text for PromptsDocumentation into prompt-ready text, without the syntax tax.
- Transcript Cleaner for LLM InputSpeech-to-text output into something worth paying to send.
- Code Comment Stripper for PromptsStrip comments from code you send to a model. Keep doc comments if you need them.
Images 7
Prompt, size and budget image generation.
- AI Image Prompt BuilderSix components in weighted order. No "masterpiece, 8k" filler.
- Negative Prompt BuilderNegative terms matched to your subject, with a warning about overloading.
- AI Image Generation Cost CalculatorAttempts multiplier included. The headline price is never what you pay.
- Image Prompt AnalyzerSeparates real descriptive terms from inherited "masterpiece, 8k" filler.
- Image Style Reference BuilderOne style block, reused across a series with only the subject changing.
- Seed and Variation PlannerA run list that isolates one variable across fixed seeds.
- Image Generation Batch PlannerAsset list in, generation count, cost and wall time out.
Reference 6
Parameters, encodings and behaviour, explained interactively.
- o200k_base vs cl100k_base ComparatorBoth encodings, both exact. Matters on any model migration.
- Temperature and Top-p SimulatorInteractive view of what your sampling settings actually change.
- max_tokens PlannerA ceiling derived from your p95, checked against window and quota.
- Streaming Latency SimulatorPrefill, first token, generation rate — and the perceived latency gain.
- LLM Pipeline Latency EstimatorMulti-step latency with serial and parallel totals compared.
- Context Rot VisualizerFill level and position against recall. Why the middle is the weak spot.
Safety 5
Check what you are about to send, and what came back.
- PII Redactor for LLM PromptsDetects emails, phones, cards, IPs and API keys. Runs locally — the point would be lost otherwise.
- Prompt Injection ScannerTen published injection patterns, with severity and position.
- Secret Scanner for PromptsAPI keys, tokens, private keys and connection strings, found before you send.
- LLM JSON Output ValidatorPull JSON out of a chatty answer and check the contract holds.
- AI Agent Guardrail BuilderRefusals, confirmations and prohibitions, grouped and precedence-stated.
How these fit together
Most work here follows the same path. Measure a real prompt in the token counter, look at where the tokens went in the tokenizer playground, strip the waste with the prompt optimizer, and price the result at your real volume in the cost calculator.
Building rather than measuring? The prompt builder, agent builder, skill builder and tool schema builder are proper forms rather than text boxes, and each one shows what the thing you are building will cost on every request.
The model price table underpins all of it, and the guides explain the reasoning behind each number.