PricingEngine — JavaScript

The PricingEngine is the pure calculation core. No database dependency.

Creating an Engine

import { PricingEngine } from "@apoorwv/ducto";

// From a dict (testing, stateless)
const engine = PricingEngine.fromDict({
  version: 1,
  models: {
    "gpt-4": "input_tokens * (0.01 / 1000) + output_tokens * (0.03 / 1000)",
    "_default": "input_tokens * (0.001 / 1000) + output_tokens * (0.003 / 1000)",
  },
});

Methods

calculate(metrics: UsageMetricsLike): CostBreakdown

const cost = engine.calculate({
  model: "gpt-4",
  inputTokens: 500,
  outputTokens: 200,
});
console.log(`Total: ${cost.total}`); // 0.011
console.log(`Model credits: ${cost.modelCredits}`);
console.log(`Tool credits: ${cost.toolCredits}`);

calculateBatch(metrics: UsageMetricsLike[]): CostBreakdown[]

Evaluate multiple metrics at once.

resolveModel(modelVersion: string): string | null

Resolve a model version string against configured model names.

hasModel(modelName: string): boolean

Check if a specific model is configured.

getFixedCost(jobName: string): number | null

Get the fixed cost for a named job.

pricingSchema(): PricingConfigData

Get the raw pricing config dict.

minBalance: number

The configured minimum balance floor.

CostBreakdown

Field	Type	Description
total	number	Total credits
modelCredits	number	Credits from model expression
toolCredits	number	Credits from tool expressions
searchCredits	number	Credits from search expressions
cacheCredits	number	Credits from cache (negative = savings)
fixedCredits	number `	null`
metadata	Record<string, unknown>	Debug info

UsageMetricsLike

Input to calculate():

Field	Type	Default
model	string	"_default"
inputTokens	number	0
outputTokens	number	0
cacheReadTokens	number	0
cacheWriteTokens	number	0
toolCalls	string[]	[]
searchQueries	number	0
searchResults	number	0
webSearchCalls	number	0
codeExecCalls	number	0
fixedJob	string `	null`