AI & prompt engineering tools
Count tokens, estimate model cost, clean up prompts and generate tool-calling schemas before you spend money on an API call.
Prompt CleanerFind and remove the smart quotes, zero-width characters and hidden Unicode that a copy-paste puts into an AI prompt — and see exactly what was in there.Prompt Token CounterCount the tokens in a prompt exactly, in your browser, with a real BPE tokenizer — then see the cost across GPT, Claude and Llama models before you send it.LLM Cost CalculatorPrice a real workload across GPT and Claude models — requests per day, tokens in and out, and the prompt cache hit rate that usually decides the bill.Context Window CalculatorSee where a model's context window actually goes — prompt, tools, history, attachments and the reply's own space — and exactly what to cut when it overflows.Prompt Diff ViewerCompare two versions of a prompt word by word, and see what the edit costs — token delta, monthly bill, and the share of the total it accounts for.Prompt OptimizerTighten a prompt with named, reversible rules, then see the token and cost saving. Deterministic — no model call, nothing rewritten silently.JSON to Prompt GeneratorTurn a JSON sample into a structured prompt template — typed field list, worked example and a JSON Schema, all derived from one document.Function Calling GeneratorPaste a TypeScript or Python function signature and get the tool-use schema for OpenAI, Anthropic and Gemini. Unreadable types are reported, never guessed.OpenAI Structured Output Schema BuilderCheck a JSON Schema against the structured-outputs strict subset, or build one from a sample response. Finds why the API returns a 400.AI Output FormatterRecover usable JSON from a model's reply — strips fences, repairs trailing commas and smart quotes, and lists every repair it made.AI Temperature & Top-p SimulatorWatch temperature, top-p, top-k and min-p reshape a token distribution, with the arithmetic shown at each stage. Paste your own logprobs, or start from the sample.