Skip to main content
aifinhub

Worked example

Running the shipped earnings-call-summarization-cost engine on the input below produces exactly this output. Continuous integration recomputes it against the engine bundle on every build, so these numbers cannot drift from the code.

Input

{
  "tool": "earnings-call-summarization-cost",
  "tickers_per_quarter": 50,
  "avg_transcript_tokens": 15000,
  "avg_summary_tokens": 800,
  "cache_hit_rate": 0.5,
  "summarization_attempts": 1
}

Output141 lines

{
  "ranked": [
    {
      "model": {
        "id": "gemini-2-5-flash-lite",
        "name": "Gemini 2.5 Flash-Lite",
        "provider": "Google",
        "inputUsdPerMtok": 0.1,
        "outputUsdPerMtok": 0.4,
        "cacheReadUsdPerMtok": 0.025
      },
      "perStockPerQuarter": 0.0012575,
      "perStockPerYear": 0.00503,
      "perQuarterTotal": 0.062875,
      "perYearTotal": 0.2515
    },
    {
      "model": {
        "id": "gemini-2-5-flash",
        "name": "Gemini 2.5 Flash",
        "provider": "Google",
        "inputUsdPerMtok": 0.3,
        "outputUsdPerMtok": 2.5,
        "cacheReadUsdPerMtok": 0.075
      },
      "perStockPerQuarter": 0.0048125,
      "perStockPerYear": 0.01925,
      "perQuarterTotal": 0.240625,
      "perYearTotal": 0.9625
    },
    {
      "model": {
        "id": "gpt-5-4-mini",
        "name": "GPT-5.4 mini",
        "provider": "OpenAI",
        "inputUsdPerMtok": 0.75,
        "outputUsdPerMtok": 4.5,
        "cacheReadUsdPerMtok": 0.375
      },
      "perStockPerQuarter": 0.0120375,
      "perStockPerYear": 0.04815,
      "perQuarterTotal": 0.6018749999999999,
      "perYearTotal": 2.4074999999999998
    },
    {
      "model": {
        "id": "claude-haiku-4-5",
        "name": "Claude Haiku 4.5",
        "provider": "Anthropic",
        "inputUsdPerMtok": 1,
        "outputUsdPerMtok": 5,
        "cacheReadUsdPerMtok": 0.1
      },
      "perStockPerQuarter": 0.01225,
      "perStockPerYear": 0.049,
      "perQuarterTotal": 0.6125,
      "perYearTotal": 2.45
    },
    {
      "model": {
        "id": "gemini-3-5-flash",
        "name": "Gemini 3.5 Flash",
        "provider": "Google",
        "inputUsdPerMtok": 1.5,
        "outputUsdPerMtok": 9,
        "cacheReadUsdPerMtok": 0.15
      },
      "perStockPerQuarter": 0.019575,
      "perStockPerYear": 0.0783,
      "perQuarterTotal": 0.9787499999999999,
      "perYearTotal": 3.9149999999999996
    },
    {
      "model": {
        "id": "gemini-2-5-pro",
        "name": "Gemini 2.5 Pro",
        "provider": "Google",
        "inputUsdPerMtok": 1.25,
        "outputUsdPerMtok": 10,
        "cacheReadUsdPerMtok": 0.31
      },
      "perStockPerQuarter": 0.0197,
      "perStockPerYear": 0.0788,
      "perQuarterTotal": 0.985,
      "perYearTotal": 3.94
    },
    {
      "model": {
        "id": "claude-sonnet-4-6",
        "name": "Claude Sonnet 4.6",
        "provider": "Anthropic",
        "inputUsdPerMtok": 3,
        "outputUsdPerMtok": 15,
        "cacheReadUsdPerMtok": 0.3
      },
      "perStockPerQuarter": 0.03675,
      "perStockPerYear": 0.147,
      "perQuarterTotal": 1.8375,
      "perYearTotal": 7.35
    },
    {
      "model": {
        "id": "claude-opus-4-8",
        "name": "Claude Opus 4.8",
        "provider": "Anthropic",
        "inputUsdPerMtok": 5,
        "outputUsdPerMtok": 25,
        "cacheReadUsdPerMtok": 0.5
      },
      "perStockPerQuarter": 0.06125,
      "perStockPerYear": 0.245,
      "perQuarterTotal": 3.0625,
      "perYearTotal": 12.25
    },
    {
      "model": {
        "id": "gpt-5-5",
        "name": "GPT-5.5",
        "provider": "OpenAI",
        "inputUsdPerMtok": 5,
        "outputUsdPerMtok": 30,
        "cacheReadUsdPerMtok": 2.5
      },
      "perStockPerQuarter": 0.08024999999999999,
      "perStockPerYear": 0.32099999999999995,
      "perQuarterTotal": 4.012499999999999,
      "perYearTotal": 16.049999999999997
    }
  ],
  "models": [
    "claude-sonnet-4-6",
    "claude-opus-4-8",
    "claude-haiku-4-5",
    "gpt-5-5",
    "gpt-5-4-mini",
    "gemini-2-5-pro",
    "gemini-3-5-flash",
    "gemini-2-5-flash",
    "gemini-2-5-flash-lite"
  ]
}

Frequently asked questions

What does the Earnings-Call Summarization Cost methodology page document?
Pricing snapshot, cost formulas, and assumptions behind the AI Fin Hub Earnings-Call Summarization Cost Calculator, with dated vendor sources. It states the formulas, assumptions, data sources, limitations, and reproducibility steps behind the Earnings-Call Summarization Cost, in the Finance category.
When was the Earnings-Call Summarization Cost methodology last reviewed?
This methodology was last reviewed on 2026-05-08. The matching tool is at https://aifinhub.io/earnings-call-summarization-cost/.
Are the Earnings-Call Summarization Cost numbers reproducible?
Yes. This page embeds a worked example whose output is the verbatim result of running the shipped earnings-call-summarization-cost engine on a fixed input; the embedded JSON is recomputed and diffed against the engine in CI, so the numbers cannot drift from the code.

Methodology · Tool · Last updated 2026-05-08

How Earnings-Call Summarization Cost works

Pricing snapshot, cost formula, and caveats for the Earnings-Call Summarization Cost Calculator.

Cost formula

fresh_input_tok  = transcript_tok · (1 − cache_hit_rate)
cached_input_tok = transcript_tok · cache_hit_rate

input_cost  = fresh_input_tok  · price_input  / 1e6
            + cached_input_tok · price_cache  / 1e6
output_cost = summary_tok · price_output / 1e6

cost_per_attempt          = input_cost + output_cost
cost_per_stock_per_quarter = cost_per_attempt · attempts
cost_per_stock_per_year    = cost_per_stock_per_quarter · 4
total_universe_per_year    = cost_per_stock_per_year · tickers

Pricing snapshot — as of 2026-05-25

Prices in USD per million tokens. Listed input/output (no batch discount). Cache read price is the discounted rate vendors charge after a cache write has been paid at full input rate.

  • Anthropic Claude Sonnet 4.6: input $3.00, output $15.00, cache read $0.30.
  • Anthropic Claude Opus 4.8: input $5.00, output $25.00, cache read $0.50.
  • Anthropic Claude Haiku 4.5: input $1.00, output $5.00, cache read $0.10.
  • OpenAI GPT-5.5: input $5.00, output $30.00, cache read $2.50.
  • OpenAI GPT-5.4 mini: input $0.75, output $4.50, cache read $0.375.
  • Google Gemini 2.5 Pro: input $1.25, output $10.00, cache read $0.31.
  • Google Gemini 3.5 Flash: input $1.50, output $9.00, cache read $0.15 (frontier agent-tier, not a budget model — its output is ~3.6x Gemini 2.5 Flash).
  • Google Gemini 2.5 Flash: input $0.30, output $2.50, cache read $0.075.
  • Google Gemini 2.5 Flash-Lite: input $0.10, output $0.40, cache read $0.025 (cheapest tier).

Assumptions

  • Cache hit applies only to the system-prompt and few-shot prefix; the transcript itself is treated as cold (uncached) input.
  • Tokens are model-tokenizer agnostic — we report a single transcript-token figure. In practice tokenizers differ by 5–15% across vendors.
  • Output tokens are typical summary length; longer multi-section outputs scale linearly.

Limitations

  • Pricing changes. The snapshot date is the only thing on this page that's authoritative — verify with vendor pricing pages before committing.
  • Batch APIs (Anthropic, OpenAI) discount further, typically 50%. Add a second tool run with halved costs if you can defer to overnight.
  • Reasoning/thinking-tokens (o-series, extended thinking) are not modelled — they are an additional output billing line.

External resources