How is cost calculated?

Cost = (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price), multiplied by the number of calls.

What does the cached input percentage do?

Providers bill repeated prompt prefixes at a discount — the calculator prices cached tokens at 25% of the normal input rate.

Are the prices up to date?

They are public list rates captured at build time and every price field is editable, so override them with your provider's current pricing page.

Does it count tokens for me?

Yes — switch on 'Count tokens from text' and paste your prompt to tokenize it exactly instead of guessing.

Is my data uploaded to a server?

No. This tool runs entirely in your browser using standard web APIs, so your input never leaves your device and nothing is logged or stored on our servers.

LLM API Cost Calculator

Estimate GPT, Claude and Gemini API spend per call and per month.

Works Offline

Privacy First

No Login

No API

Usage

Model

Count tokens from text

Input tokens per call

Output tokens per call

Number of calls

Input price (USD / 1M)

Output price (USD / 1M)

Cached input %

Cached prompt tokens are billed at 25%

Estimated cost

Input cost / call

$0.002500

Output cost / call

$0.005000

Cost per call

$0.007500

Cost × 1,000

$7.5000

If run daily (30d)

$225.0000

Total tokens

1,500,000

Same workload on every model

Model	Per call	Total
GPT-4o	$0.007500	$7.5000
GPT-4o mini	$0.000450	$0.4500
GPT-4.1	$0.006000	$6.0000
GPT-4.1 mini	$0.001200	$1.2000
o3	$0.006000	$6.0000
GPT-4 Turbo	$0.0250	$25.0000
GPT-3.5 Turbo	$0.001250	$1.2500
Claude Sonnet	$0.0105	$10.5000
Claude Haiku	$0.002800	$2.8000
Claude Opus	$0.0525	$52.5000
Gemini Flash	$0.001550	$1.5500
Gemini Pro	$0.006250	$6.2500
Llama 3.3 70B	$0.000950	$0.9500
Mistral Large	$0.005000	$5.0000

Prices are public list rates and are editable above — always confirm with your provider's pricing page.

About the LLM API Cost Calculator

Enter token counts or paste your prompt, set output length, call volume and prompt-cache ratio, then compare cost per call, per run and per month across every major model. Prices are editable so you can model your own negotiated rates.

Examples

1k calls

1,000 in / 500 out on GPT-4o

Output

$7.50 total

Keyboard shortcuts

Copy the main outputCtrl / ⌘ + Shift + C
Download the resultCtrl / ⌘ + S
Share this toolCtrl / ⌘ + Shift + S
Reset the inputsAlt + R
Open the tool search paletteCtrl / ⌘ + K

Related tools

AI Token Counter

AI & LLM

Count exact LLM tokens for GPT, Claude and Gemini prompts.

LLM Context Window Calculator

AI & LLM

See if your system, context and user messages fit the model window.

AI PII & Secret Redactor

AI & LLM

Strip emails, keys, tokens and personal data before prompting an LLM.

AI Tool Schema Builder

AI & LLM

Build function-calling schemas for OpenAI, Claude, Gemini, MCP and the AI SDK.

JSONL ↔ JSON Converter

AI & LLM

Convert JSON Lines to a JSON array and back again.

JSONL Formatter

AI & LLM

Pretty-print, minify, sort and deduplicate JSON Lines files.

Frequently asked questions

Version 1.0.0 · Updated 2026-08-14 · Runs entirely in your browser