Guides
Long-tail topics in depth: tokens, tiktoken, vendor counting, and conversions — each linked to tools you can try.
- What Is a Token? AI Models, APIs & Context Windows
Tokens are how LLMs meter text—not pages or words. Learn what they are, how they differ from word count, and when to use a browser token counter before you paste.
- Tiktoken vs Approximate Token Counts - Browser Guide
When browser counts match OpenAI tiktoken encodings (o200k, cl100k) and when Claude or Gemini stays approximate. How to read the labels and verify on the API.
- OpenAI, ChatGPT & GPT Token Counting Explained
Count OpenAI and ChatGPT prompts before you paste: tiktoken-style encodings, GPT-4 length checks, and what ChatGPT UI overhead does not show in a plain counter.
- Claude & Anthropic Token Counting (Approximate)
Size Claude prompts in the browser with labeled estimates—why Anthropic has no static tiktoken twin, how to plan context, and when to verify on the API.
- Gemini Token Counter Online - What “Approximate” Means
Estimate Gemini token length before a long paste. Why Google has no drop-in browser encoding, how our counter labels uncertainty, and when to trust Google AI Studio.
- Tiktoken in Python - Encodings, GPT Length & Browser Check
What Python tiktoken does, how o200k_base and cl100k_base map to GPT length, and when a browser token counter is enough for a sanity check outside your IDE.
- GPT-4o Context Window, Max Tokens & 128k Fill %
What GPT-4o max tokens and 128k mean in practice—fill percentage, reply headroom, and how to check a long paste before the model truncates or forgets.
- Words to Tokens & Tokens to Words - 32k, 128k, 1M
Planning ratios for words ↔ tokens: 200 tokens, 32k, 128k, 1 million tokens to words. Limits of fixed ratios and when to paste real text into the counter.
- LLM & Online Token Counter - Browser, Local, No Upload
What a good online LLM / AI token counter should do: count locally, switch OpenAI / Claude / Gemini modes, label estimates—without a pile of duplicate keyword pages.