LLM API Cost Calculator
Compare what your workload would cost on OpenAI, Anthropic and Google models, or plug in your own price.
Runs in your browser. Nothing you enter is uploaded.Estimate input tokens from your text
This is a rough estimate (about 4 characters per token for English). Each model counts tokens a little differently, so treat it as a guide.
Add your own model or price
List prices in USD per 1 million tokens, checked on 19 Oct 2026 from the official pricing pages: OpenAI, Anthropic and Google. Prices change often, so confirm on the provider's site before you commit. Caching, batch discounts, images, tool use and taxes are not included.
About this tool
Enter how many requests you expect each month and the average number of input and output tokens per request. The calculator multiplies them by each model's published price and shows the cost per request, per month and per year, so you can see which model fits your budget before you build.
- Input tokens are everything you send: instructions, context, documents and the user's message.
- Output tokens are what the model writes back. They usually cost several times more than input tokens.
- Quick examples fill in typical numbers for a chatbot, summarizer, question-answering bot and content writer.
Prices are list prices for standard usage. Real bills can be lower with prompt caching or batch processing, and higher if you use very long prompts, images or built-in tools. If your model or provider is not listed, add your own price under "Add your own model or price".
Frequently asked questions
How much does one API request cost?
Multiply the input tokens by the input price and the output tokens by the output price, both per million tokens, then add them. For example, 1,500 input tokens at $2 per million plus 500 output tokens at $10 per million costs about $0.008 per request.
What is a token?
A token is a small piece of text, roughly four characters or three quarters of a word in English. Providers charge by tokens, not by words. Use the "Estimate input tokens from your text" box for a quick guess.
Why are output tokens more expensive than input tokens?
Generating text takes more computing work than reading it, so providers price output tokens higher, often three to six times the input price.
Are these prices up to date?
They were checked against each provider's official pricing page on 19 Oct 2026. Providers change prices often, so always confirm on the official page before you commit to a budget.
What is not included in the estimate?
The calculator uses standard list prices only. Prompt caching, batch discounts, fine-tuning, image or audio inputs, tool and search fees, rate-limit tiers and taxes are not included.
Is my data sent anywhere?
No. The numbers and any text you paste stay in your browser and are never uploaded or stored.
Other free tools
Word & Character Counter
Count words, characters, sentences and reading time, with top keywords and limit checks.
Text Case Converter
Switch text between upper, lower, title, sentence, camel, snake and kebab case.
UTM Link Builder
Build campaign-tracked URLs with source, medium and campaign in seconds.
Image Compressor
Shrink JPG, PNG and WebP files in your browser. Nothing is uploaded.
PNG / JPG / WebP Converter
Convert images between PNG, JPG and WebP right in your browser.