Frequently Asked Questions

How many tokens is 1,000 words?
Roughly 1,300–1,500 tokens for English text, though this varies by tokenizer. GPT models average around 1.3 tokens per word, while other models may differ slightly based on how they split text.

How do you calculate AI API cost?
Cost = (input tokens × input price) + (output tokens × output price), based on the specific model’s per-token pricing. Paste your text into our calculator to see the exact breakdown for 45+ models.

What’s the difference between GPT and Claude token pricing?
Pricing varies by provider and model tier. Generally, smaller/faster models (like GPT-4o mini or Claude Haiku) cost less per token than larger flagship models (like GPT-4o or Claude Opus). Check our calculator for current rates across both.

How many tokens fit in a context window?
This depends on the model. Context windows range from 8K tokens on older models up to 1M+ tokens on newer ones like Gemini 1.5 Pro. Check our context window guide for a full comparison.

Do you store the text I paste in?
No. Everything runs in your browser. We don’t save, log, or transmit your text anywhere.