— Chatbot & AI

LLM API Cost Calculator

Estimate what an LLM API actually costs — pick a model, set tokens per call and monthly volume, and see cost per call, day, month and year.

Input $3.00 / output $15.00 per 1M tokens.
$0.01Cost / call
$4.00Cost / day
$120.00Cost / month
$1,440.00Cost / year
Prices are illustrative figures as of 2026 and may be out of date. Always verify the current rate with the model provider before budgeting.
— What it does

The LLM API Cost Calculator is a free tool that estimates how much a large language model API will cost based on the model you choose, the input and output tokens per call, and how many calls you make each month. Pick a 2026 Claude or GPT model from the menu (or enter custom prices), and it instantly shows cost per call, per day, per month and per year so you can budget an AI feature before you build it.

  • Built-in 2026 price table for Claude Opus, Sonnet and Haiku plus GPT-4.1, GPT-4.1 mini and GPT-4o.
  • Separate input and output token pricing, because output usually costs more.
  • Custom model option with your own per-million input and output prices.
  • Runs entirely in your browser — nothing you type is uploaded to a server.

How to use it

1

Choose a model

Select a Claude or GPT model from the list, or pick Custom to type in your own input and output prices per million tokens.

2

Enter tokens and volume

Set the average input tokens and output tokens per call, then how many calls you expect each month.

3

Read your projected cost

The calculator instantly shows the cost per call, per day, per month and per year so you can size your budget.

Frequently asked

Are these LLM prices accurate?
The built-in prices are illustrative figures dated to 2026 and are meant for quick estimates only. Provider pricing changes often, so confirm the current per-token rate on the model provider’s official pricing page before you commit to a budget.
How do I estimate tokens per call?
As a rough rule, one English token is about four characters or three-quarters of a word. Add your system prompt and retrieved context to the user message to estimate input tokens, and use a typical reply length for output tokens. A token counter tool gives an exact count.
Why are input and output priced separately?
Most providers charge more for output (generated) tokens than input (prompt) tokens. This calculator multiplies each by its own rate, so chatty replies and long contexts are both reflected accurately.
Is my data sent anywhere?
No. The calculation runs entirely in your browser with JavaScript. Nothing you enter is uploaded, stored, or sent to any server.

Related tools

LLM Token Counter

Paste any text and get a live estimate of how many tokens it will use — plus word and character counts — right in your browser.

Open tool →

Chatbot ROI Calculator

See what an AI support agent actually saves you — deflected conversations, hours returned, and monthly payback, in real numbers.

Open tool →

Support Ticket Deflection Calculator

See how much an AI agent saves by deflecting support tickets — using your real cost per ticket, not guesswork.

Open tool →

← All free tools

— Built by saavos

These tools are free. So is the first version of your agent.

saavos is the AI agent that lives on your website — themed to match your design, answering visitors from your own content, and telling you what they actually want to know. Paste your URL and see it answer, before you install anything.

Make my site feel alive