AI & Prompt Tools

Estimate token counts for GPT, Claude, and Llama-style models as you type.

Estimate LLM API costs from input/output token counts across popular models.

Build reusable AI prompt templates with {{variable}} placeholders and instant preview.

Convert JSON to TOON, a compact token-oriented format that reduces token usage in LLM prompts.

Generate Model Context Protocol (MCP) server configuration for Claude Desktop, Claude Code, Cursor and VS Code from a command, arguments and environment variables.

Create an llms.txt file that points AI assistants and LLM crawlers to your most important pages, following the llmstxt.org markdown format.

Generate an AGENTS.md file with setup, build, test, code style and PR instructions so AI coding agents can work in your repository correctly.

Estimate whether your text fits in the context window of popular LLMs such as GPT, Claude, Gemini and Llama, with an approximate token count and percentage used.

Convert a function/tool definition between OpenAI function calling, Anthropic tool use and Gemini function declaration formats.

Calculate cosine similarity, dot product, Euclidean distance and vector magnitudes between two embedding vectors pasted as JSON or comma-separated numbers.

Preview how a document is split into chunks for retrieval-augmented generation, with adjustable chunk size, overlap and recursive or fixed-size strategies.

Compare two versions of an LLM prompt side by side with word-level highlighting and an approximate token-count change.

Compare LLM API costs for standard, batch, and prompt-cached workloads to see how much a batch discount and caching could save on your volume.

Paste embedding vectors and get the cosine similarity, dot product and Euclidean distance between every pair.