Pricing & Cost Calculation — ML Junction docs

Route prices are returned in USD per one million tokens. pricing=null means no verified active price is available; it does not mean the route is free.

Field · Unit · Meaning
input_per_mtok · USD / 1,000,000 tokens · Uncached input tokens
cached_input_per_mtok · USD / 1,000,000 tokens · Input tokens served from provider cache
output_per_mtok · USD / 1,000,000 tokens · Generated output tokens
effective_from · UTC timestamp · Beginning of the active price period
effective_to · UTC timestamp or null · End of the price period
source · URL · Pricing evidence/source

uncached_input_tokens = input_tokens - cached_input_tokens

input_cost =
  uncached_input_tokens / 1,000,000 * input_per_mtok

cached_input_cost =
  cached_input_tokens / 1,000,000 * cached_input_per_mtok

output_cost =
  output_tokens / 1,000,000 * output_per_mtok

estimated_total =
  input_cost + cached_input_cost + output_cost

function estimateCost({ inputTokens, cachedInputTokens, outputTokens, pricing }) {
  if (!pricing) return null;

  const million = 1_000_000;
  const cached = Math.min(cachedInputTokens ?? 0, inputTokens);
  const uncached = Math.max(0, inputTokens - cached);

  return (
    (uncached / million) * Number(pricing.input_per_mtok ?? 0) +
    (cached / million) * Number(pricing.cached_input_per_mtok ?? pricing.input_per_mtok ?? 0) +
    (outputTokens / million) * Number(pricing.output_per_mtok ?? 0)
  );
}

The receipt actual_charge_usd is authoritative for the completed request. Client-side estimates cannot predict provider-specific reasoning, cache, retry, or fallback usage exactly.

Canonical URL: https://mljunction.com/docs/pricing-costs