LLM Cost Estimation and Comparison
Calculate token costs and compare up to 4 models side-by-side.
Pricing last updated: Loading...
Your Prompt
Cost Calculation
Frequently Asked Questions
What are tokens in LLM APIs?
Tokens are small pieces of text that AI models process. Roughly 1 token = 4 characters or 0.75 words in English. Your prompt uses input tokens; the AI’s reply uses output tokens.
Why is output usually more expensive than input?
Output tokens are generated one by one (sequential), while input tokens are processed all at once (parallel). This makes output 2–5× more expensive depending on the model.
How accurate is the token counter?
It uses a fast character-based approximation (~4 characters = 1 token). It’s accurate enough for cost estimation. Official SDKs give exact counts, but this is very close for most English text.
Where does the pricing data come from?
It is loaded live from LiteLLM’s community-maintained pricing file. Prices are updated automatically whenever LiteLLM updates their data (usually weekly).
Can I use this tool offline?
Yes! After the first load, the tool works completely offline. Only pricing data needs internet on first visit (it caches afterward).
How do I compare multiple models?
Search and select a model, click “Add to Compare”. You can add up to 4 models. Use the × button to remove any model and add a different one.
Is my data private?
Yes. Everything runs in your browser. No data is sent to any server. Your prompts and calculations stay 100% private.
Check respective LLM websites for exact pricing and details. This is an estimation tool and may not reflect real-time changes or discounts. Always verify before making decisions.