Free tool • Runs in your browser
AI API cost calculator
Estimate per-request, daily and monthly AI API costs across Claude, OpenAI and Gemini models.
Quick answer
API cost equals input tokens times the input price, plus output tokens times the output price, with prices quoted per million tokens. Multiply by your request volume for a monthly figure. Output tokens usually cost several times more than input tokens.
How to use it
- Pick a model preset, or enter your own prices.
- Enter average input tokens, output tokens and requests per day.
- Read the cost per request, per day and per 30-day month.
Example
Input $2 and output $10 per 1M tokens 1,000 input tokens, 500 output tokens 1,000 requests a day
Per request: $0.007 Per day: $7.00 Per 30 days: $210.00
Common errors and how to fix them
- The real bill is higher
- Remember the system prompt, conversation history and tool results are input tokens on every request.
- A preset looks out of date
- Providers change prices often. Edit the price fields using the provider's current pricing page.
Frequently asked questions
How much does an AI API cost?
It depends on the model and how many tokens you use. Prices are usually quoted per million input and output tokens, and this calculator turns them into a per-request and monthly estimate.
How much does the OpenAI API cost?
OpenAI prices vary by model, so choose a preset here or enter current prices from OpenAI's pricing page. Presets may be out of date, so check them before budgeting.
How is AI API cost calculated?
Multiply input tokens by the input price and output tokens by the output price, using per-million-token rates. Then multiply by your number of requests.
Why do output tokens cost more than input tokens?
Providers commonly charge more for generated text than for text read by the model, so long answers can drive up your bill.
Are AI APIs free to use?
Most production use is paid, though some providers offer free tiers or trial credits. Check the provider's current terms.
How can I reduce my AI API bill?
Use a smaller model where quality holds, shorten prompts, limit output length, and use prompt caching or batch processing where available.
Are the prices in this calculator live?
No. The presets were checked on 5 November 2026 and do not update automatically, so you can edit each price.
Does this calculator include caching or batch discounts?
No. It uses standard list prices, so your real cost can be lower if you use those features.
Why is my real bill higher than this estimate?
System prompts, conversation history, tool definitions and retries all add tokens. Use realistic averages from your own usage data.
Is what I enter uploaded?
No. The calculation runs in your browser and nothing is sent to Quecko.
More AI tools
Need something built for your business?
Quecko designs and builds AI, Web3 and custom software products.