Best AI & LLM Tools

Count exact LLM tokens for GPT, Claude and Gemini prompts.

See if your system, context and user messages fit the model window.

Estimate GPT, Claude and Gemini API spend per call and per month.

Audit prompts for vague wording, missing formats and leaked secrets.

Validate JSONL and fine-tuning datasets line by line.

Pretty-print, minify, sort and deduplicate JSON Lines files.

Convert JSON Lines to a JSON array and back again.

Split documents into token-sized overlapping chunks for embedding.

Check that a model's JSON reply matches your JSON Schema.

Build function-calling schemas for OpenAI, Claude, Gemini, MCP and the AI SDK.

Validate Model Context Protocol tool definitions before you ship them.

Strip emails, keys, tokens and personal data before prompting an LLM.

Convert function-calling schemas between OpenAI, Anthropic, Gemini and MCP.

Wrap any JSON Schema into a ready-to-use function-calling tool.

Compare two prompt versions word by word with a token delta.

Compare two model responses to measure drift between runs or models.

Fit as many RAG chunks as possible into a model context budget.

Remove exact and near-duplicate rows from fine-tuning datasets.

Profile a JSONL training set: token stats, roles, duplicates and cost.

Convert between OpenAI chat, ShareGPT, Alpaca and prompt/completion.

Cosine, dot product and distance between two embedding vectors.

Inspect dimensions, norm, mean and spread of an embedding vector.

Generate an MCP, OpenAI or Anthropic tool schema from example arguments.