Tools

Browser-based utilities for working with LLMs. 9 tools so far. All run client-side — nothing you paste leaves your machine.

Tokens & Cost

Count tokens and estimate cost across GPT, Claude, Gemini, Llama and DeepSeek side-by-side.

Paste system, retrieved docs, history and user message; see per-model fill % and how much budget is left.

Compare two prompts side-by-side with character, word, and token-level deltas plus an inline diff.

Auto-detect {{var}}, ${var}, or <var> syntax. Preview substitutions. Export as Python or TypeScript.

Trim verbose phrases, politeness fillers, and imperative softeners. See token + dollar savings projected across models.

Paste a document, see how it gets chunked under fixed, recursive, or markdown-aware strategies side-by-side.

Paste two or more texts; see pairwise cosine similarity with a free in-browser embedding model.

Paste sample JSON; get an OpenAI-strict or Anthropic-tool schema with the structured-output gotchas handled.

Paste a response; preview how it streams at various tokens/sec. Design chat UX without burning API calls.