LLM Token Counter
Paste any text to estimate how many tokens it uses in an LLM prompt, plus characters and words. Everything runs in your browser — nothing is sent anywhere.
Estimated tokens
38
Characters
172
Words
26
Likely range: 32–44 tokens (varies by model and tokenizer).
This is a fast estimate. For exact, model-specific counts use the provider's tokenizer (e.g. Anthropic's count_tokens endpoint or OpenAI's tiktoken).
Counting tokens means you're building with LLMs
Want it shipped to production instead of stuck in a prototype? Yiriba does LLM integration end to end — book a free call.
Book a free call