LLM Tools for Prompts, Tokens & Integration
Everyday utilities for wiring language models into real products: count tokens and compare what a workload will cost on each provider, split documents for retrieval, debug server-sent event streams, convert chat formats, and set up MCP servers and llms.txt files.
TOK LLM Token Counter Count tokens exactly with OpenAI’s o200k_base (GPT-4o, GPT-4.1, GPT-5, o-series) and cl100k_base (GPT-4, GPT-3.5) tokenizers, and see how your text is split. Runs offline in your browser. MD AI Markdown Cleaner Paste an answer from ChatGPT, Claude, Gemini or DeepSeek and remove the **, ##, backticks and citation markers. Get clean plain text, or copy as formatted rich text for Word, Google Docs, email and Feishu. MCP MCP Config Generator Fill in an MCP server once and get the correct config for Claude Desktop, Claude Code, Cursor, VS Code and Windsurf — local (stdio) or remote (HTTP) servers, with env vars and headers. SSE LLM Stream (SSE) Parser Paste a raw streaming response (Server-Sent Events or NDJSON) from OpenAI, Anthropic Claude, Google Gemini, Ollama or any OpenAI-compatible API, and get the final text, reasoning, tool calls and token usage. {{}} Prompt Template Filler Paste a prompt template with {{variables}}, {placeholders} or ${vars}. A form is generated for each variable, the filled prompt previews live with its token count, and you can export ready-to-use Python or JavaScript code. RAG RAG Text Chunker Preview how a document is split into chunks for embeddings and RAG. Recursive splitting by paragraphs, lines and sentences (Chinese punctuation included), chunk size in tokens or characters, overlap, and JSON export. llms llms.txt Generator Create an llms.txt file for your website or docs: a Markdown index that tells LLMs and AI agents which pages matter. Import links from your sitemap.xml and download the result. $/M LLM API Cost Calculator Estimate per-request, daily and monthly API cost across OpenAI, Anthropic, Google and DeepSeek models. Accounts for prompt caching, long-context price tiers and context-window limits. API LLM API Playground Send requests to OpenAI, Anthropic, DeepSeek, OpenRouter, Ollama or any OpenAI-compatible API with your own key. Watch streaming output, time to first token, usage, tool calls and structured output — and copy the request as curl.