Paste text that is too long for one message and get numbered parts that fit your token limit, each wrapped with instructions so Claude, ChatGPT, or Gemini waits for every part before answering.
Splitting happens at paragraph and sentence boundaries, counted in real tokens, entirely in your browser.
Need exact Claude token counts? Use the Claude Tokenizer.
0 characters. Nothing leaves your browser.
Counted with OpenAI's o200k tokenizer. Claude usually counts a little higher, so stay comfortably below your model's real limit.
Paste your text and pick a per-part token limit. The splitter counts real tokens, cuts at paragraph and sentence boundaries where possible, and wraps every part with instructions telling the AI to acknowledge each part and wait until all parts have arrived before responding.
Any chat AI: Claude, ChatGPT, Gemini, Grok, and others. The wrapper instructions are plain text that every chat model understands.
Counts use OpenAI's open o200k tokenizer, the same one GPT-4o and newer models use. Claude's tokenizer usually counts slightly higher, so leave some headroom below your model's real limit. For exact Claude counts, use the tokenizer on our home page.
Set it comfortably below your model's context window so there is room for the conversation itself. 8,000 tokens per part is a safe default for modern chat AIs; go smaller for older models or long-running chats.
No. Counting and splitting run entirely in your browser. Your text never leaves your device.
MemoryPlugin gives Claude, ChatGPT, Gemini, and 20+ other AI tools one shared long-term memory and a searchable chat history. Tell one AI something once, and the rest have it from your next conversation.
Try MemoryPlugin free