token-dollars

Calculate costs for AI model API usage based on token consumption and pricing.

Installation

npm i token-dollars

Usage

Import

import { Cost, Store } from 'token-dollars';

Calculate Cost

Calculate the total cost for a model based on usage statistics:

const usage = {
  total_text_input_tokens: 1000000,
  total_text_output_tokens: 500000,
  total_cached_text: 200000
};

const result = Cost('gpt-4o', usage);
console.log(result);
// {
//   model: 'gpt-4o',
//   total: 3.75,
//   breakdown: {
//     textInputCost: 2.5,
//     cachedTextInputCost: 0.25,
//     textOutputCost: 5,
//     audioInputCost: 0,
//     cachedAudioInputCost: 0,
//     audioOutputCost: 0,
//     whisperCost: 0
//   }
// }

Usage Object

The usage parameter accepts the following optional properties:

• total_text_input_tokens - Total number of text input tokens
• total_cached_text - Total number of cached text tokens
• total_text_output_tokens - Total number of text output tokens
• total_audio_input_tokens - Total number of audio input tokens
• total_cached_audio - Total number of cached audio tokens
• total_audio_output_tokens - Total number of audio output tokens
• input_Transcript_Duration_whisper - Whisper transcription duration in seconds

Audio and Whisper Example

const usage = {
  total_text_input_tokens: 500000,
  total_audio_input_tokens: 1000000,
  total_audio_output_tokens: 500000,
  input_Transcript_Duration_whisper: 120 // 2 minutes
};

const result = Cost('gpt-realtime', usage);
console.log(result.total); // Total cost including audio and whisper

Supported Models

The package includes pricing for the following models:

OpenAI Models

• gpt-5
• gpt-5-mini
• gpt-5-nano
• gpt-5-chat-latest
• gpt-5-pro
• gpt-4.1
• gpt-4.1-mini
• gpt-4.1-nano
• gpt-4o
• gpt-4o-2024-05-13
• gpt-4o-mini
• gpt-realtime
• gpt-realtime-mini

Google Models

• gemini-2.5-flash-native-audio-latest

API

Cost(model, usage)

Calculates the total cost for a given model based on usage statistics.

Parameters:

• model (string) - The model identifier (must exist in Store)
• usage (object) - Usage statistics object containing token counts and transcription duration

Returns:

• object - Cost calculation result
  • model (string) - The model identifier
  • total (number) - Total cost (rounded to 6 decimal places)
  • breakdown (object) - Detailed cost breakdown by component
    • textInputCost (number)
    • cachedTextInputCost (number)
    • textOutputCost (number)
    • audioInputCost (number)
    • cachedAudioInputCost (number)
    • audioOutputCost (number)
    • whisperCost (number)

Store

An object containing pricing information for all supported models. Each model entry includes:

• pricing - Pricing per million tokens or per minute (for Whisper)
• asp - API service provider (e.g., "openai", "google")
• wssUrl - WebSocket URL (for realtime models)

Pricing Notes

• Token costs are calculated per million tokens
• Whisper transcription costs are calculated per minute
• Costs are rounded to 6 decimal places
• Missing usage properties default to 0

License

ISC