Skip to content
ENExplore Calculators

Reranking Cost Calculator

Work out reranking cost instantly with clear inputs, formula shown and shareable results.

About Reranking Cost Calculator

A cross-encoder reranker scores every candidate against the query, so cost scales with candidates multiplied by tokens per candidate — not with the number of chunks finally used. Retrieving 50 candidates and reranking to 5 costs ten times as much scoring as no reranking at all, which is why candidate depth is the main cost lever in a RAG pipeline.

Formula

Reranking cost

tokens per query = candidates x tokens per candidate; cost = queries x tokens per query x price / 1,000,000

Worked example

With the default values below, Reranking Cost Calculator returns Monthly reranking cost of $550.00. Change any input above and every figure here is recalculated in your browser.

Inputs used

Queries per monthminimum 1
200,000
Candidates reranked per queryminimum 1
50
Tokens scored per candidateminimum 1
220
Reranker price per million tokensminimum 0
0.25

Results

Monthly reranking cost
$550.00
Tokens scored per month
2,200,000,000
Reranking cost per query
$0.002750
Tokens scored per query
11,000

Step by step

  1. 1Values used
  2. 2Reranking cost
  3. 3Monthly reranking cost= 550.00
  4. 4Tokens scored per month= 2,200,000,000
  5. 5Reranking cost per query= 0.002750
  6. 6Tokens scored per query= 11,000

Assumptions and limits

  • The result is derived only from the 4 inputs listed above. Anything not among them is not part of the calculation.
  • In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
  • Figures are rounded for display to 6 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.

How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.

Frequently Asked Questions

Is reranking worth the extra cost?

Usually yes. Cross-encoders typically lift retrieval quality substantially over pure vector similarity because they see the query and document together rather than comparing independent embeddings.

How deep should the candidate list be?

Start at 25 to 50. Going deeper increases cost linearly while recall gains flatten, so measure recall@k on your own data to find the knee.

Related Calculators

Reranking Cost Calculator – Calculate Monthly reranking cost