NeuroGenesysHow many tokens is this?
Paste a prompt, a document or a source file. The tokenizer runs in your browser, so nothing is uploaded; you get the token count, whether the text fits a model's context window with room for the reply, and what it costs to send.
Free · runs in your browser · updated
1 · Your text
Counted in your browser. The text is never uploaded.
2 · Count
Counted with o200k_base, the tokenizer of OpenAI's current models. Claude and Gemini use their own tokenizers, so their counts for the same text differ; treat the figure as an estimate for them. English prose runs about four characters per token; code, numbers and non-Latin scripts take more tokens.
3 · Does it fit?
- Claude Fable 5.11M contextfits
- Claude Opus 5.51M contextfits
- Claude Sonnet 5.51M contextfits
- Claude Haiku 5.51M contextfits
- Claude Haiku 4.5200K contextfits
Only models whose provider pricing page states a context window are listed.
4 · Cost to send it as input
One request, input only, uncached, at list prices as of Nov 09, 2026. For output and volume, use the LLM API cost calculator.
Questions
How many tokens is a word?
In English, about 1.3 tokens per word, or four characters per token. Code, numbers, URLs and languages written in non-Latin scripts use more tokens for the same length of text.
Which tokenizer does this use?
o200k_base, the tokenizer OpenAI's current models use. Claude and Gemini have their own tokenizers, so for them the count is an estimate: the same text can come out somewhat higher or lower.
What is a context window?
The most tokens a model can take in one request, counting your input and the reply it writes. If your text plus the reply would exceed it, the request fails or has to be split. That's why the checker reserves tokens for the reply.
Is my text sent anywhere?
No. The tokenizer is downloaded once and runs in your browser. The text you paste or load never leaves your machine.
Related
- Free toolLLM API cost calculator
- Free toolTest-Time Compute Cost EstimatorWhat Best-of-N and self-consistency cost per query, and the accuracy they can buy: oracle coverage and majority vote against the number of samples.
- Free toolAI Eval Sample Size CalculatorHow many eval items you need: the margin of error on one model's accuracy, and the sample size to detect a difference between two models, paired or not.
- Free toolLLM Training Compute CalculatorTraining FLOPs from parameters and tokens (6ND), GPU-hours at a realistic utilization, wall-clock time and cost — or the compute-optimal model for a budget.
- Free toolVRAM Calculator: Can I Run This LLM?GPU memory for an LLM at any quantization and context length — weights, KV cache and overhead — and which GPUs and Apple Silicon Macs can hold it.
- Free toolLLM Inference Speed Estimator (Tokens per Second)Tokens per second and time to first token for a model on a GPU or Mac, from memory bandwidth and compute, and how batching changes throughput.
- Free toolAgent Tool Count CalculatorHow often an agent picks the wrong tool as its library grows, from published benchmarks: every tool in the prompt, embedding or BM25 shortlists, with the measured range marked.
- Free toolLLM Judge Agreement CalculatorCheck an LLM-as-judge against human labels: Cohen's kappa with a 95% interval, the confusion matrix, sensitivity and specificity, and how many human labels the judge is worth.
- Free toolEU AI Act Risk CheckerAnswer a few questions to see your EU AI Act risk tier, the obligations with their articles, and the deadlines after the 2026 Digital Omnibus.
