Loading page
About this tool
Estimate monthly OpenAI GPT API spend from daily request volume, average token counts, cached-input share and batch discount.
This calculator projects monthly OpenAI GPT API spend from three numbers — requests per day, average input tokens and average output tokens per request — multiplied by the model's per-1M-token input and output rates. It models the cached-input discount and the Batch API's 50% rate, and every preset rate is editable so teams can match the live OpenAI pricing page exactly before committing to a budget.
Open GPT API Cost Calculator on AltFTool — it loads instantly in your browser.
Enter the values you already know.
Fine-tune the options to match your scenario.
Read the result and use it in your planning or reporting.
Bills input and output tokens separately at per-1M rates, the way OpenAI actually invoices.
Applies the cached-input rate to your cache-hit share and the 50% Batch API discount.
Presets load current published prices, and every rate field can be overridden when prices change.
Per token, with separate rates for input (prompt) and output (completion) tokens quoted in dollars per 1 million tokens. Your cost per request is input tokens times the input rate plus output tokens times the output rate, divided by one million — so a 1,000-token prompt with a 500-token answer on a $1.25/$10 model costs about $0.00625.
When the beginning of your prompt repeats across requests, OpenAI's automatic prompt caching serves those tokens at a discounted cached-input rate — for several GPT-5 family models that is 10% of the normal input price. A workload with a stable system prompt and a high cache-hit share can cut input costs substantially without any code change beyond keeping the prompt prefix identical.
50%. Batch requests are processed asynchronously within a 24-hour window and bill both input and output tokens at half the standard rate, which suits evaluations, backfills and nightly classification jobs that do not need an immediate response.
Roughly 4 characters or 0.75 English words per token, so a 300-word prompt is about 400 tokens. Real workloads vary widely — system prompts, conversation history and JSON structure all count as input tokens — so measure your own averages from the usage field in API responses rather than guessing.
Add the GPT API Cost Calculatorwidget to your blog or website — free, responsive, no signup. Just keep the “Widget by AltFTool” credit link visible.
<iframe src="https://www.altftool.com/embed/widget/gpt-api-cost-calculator"
title="GPT API Cost Calculator — free AltFTool widget"
width="100%" height="640" style="border:0;border-radius:12px;overflow:hidden"
loading="lazy" referrerpolicy="no-referrer-when-downgrade"></iframe>
<p style="font-size:12px;margin:4px 0 0">Widget by <a href="https://www.altftool.com/tools/all/gpt-api-cost-calculator?utm_source=embed&utm_medium=widget">AltFTool — free online tools</a></p>