Skip to main content
aifinhub
AI in Markets Worked Examples

Financial Document Token Estimator: Examples

The tokenization difference between providers matters at document scale. Anthropic counts roughly 3.5 characters per token; OpenAI and Google count about 4, so the same 10-K body of 72,000 characters is 20,571 tokens for Claude and 18,000 for GPT and Gemini. These scenarios fix a 10-K body and 2,000-token output, then show how that gap affects per-filing cost across providers. One-pass cost reads the filing once; synthesis re-ingests it with peer filings for a comparative analysis. List rates, no caching.

By AI Fin Hub Research · AI Fin Hub Team
Best Next MoveCalculators

Financial Document Token Estimator

Paste a 10-K, 10-Q, 8-K or earnings transcript and see token count + one-pass extraction cost across eight frontier LLMs, with cache-hit toggle.

CalculatorOpen ->

On This Page

Worked Examples

See the inputs and outcome together

Each scenario keeps the starting point, the outcome, and the actual lesson in one place so the page reads like a decision notebook, not a data dump.

  1. 1

    One-pass 10-K on a cheap model

    Reading a single 10-K body once on Claude Haiku 4.5 to extract a summary. The standard first-pass extraction job.

    20,571 input tokens, one-pass cost $0.0306, fits in context.

    Document

    10-K body (~72K chars)

    Output tokens

    2,000

    Peers

    1

    Model

    Claude Haiku 4.5

    A full 10-K reads for three cents on Haiku. The input dominates at $0.0206 because the filing is long and the output is short. For high-volume extraction this is the right tier; the filing comfortably fits the context window.

  2. 2

    Same filing, flagship model

    The identical one-pass read on Claude Opus 4.7, the choice when extraction accuracy on dense financials matters.

    20,571 input tokens, one-pass cost $0.1529, fits in context.

    Document

    10-K body (~72K chars)

    Output tokens

    2,000

    Peers

    1

    Model

    Claude Opus 4.7

    Opus is five times Haiku at $0.153 per filing, the exact ratio of their input prices since the token count is identical. The decision is purely quality versus a five-cent-per-filing premium, not a context or capability limit.

  3. 3

    Tokenizer difference on the same document

    Reading the same 10-K on GPT-5.5, which tokenizes at about 4 characters per token instead of Claude's 3.5.

    18,000 input tokens, one-pass cost $0.15, fits in context.

    Document

    10-K body (~72K chars)

    Output tokens

    2,000

    Peers

    1

    Model

    GPT-5.5

    GPT counts 18,000 tokens for the same filing that costs Claude 20,571, because its tokenizer packs more characters per token. The tokenizer alone gives a 12 percent token discount before any price difference; comparing models on price per filing, not price per token, is the only fair comparison.

  4. 4

    Five-peer synthesis

    A comparative analysis that ingests the target filing alongside five peer 10-Ks on Claude Haiku 4.5, then writes a synthesis. The realistic competitive-analysis workload.

    Synthesis input 123,426 tokens, synthesis cost $0.1334 (versus $0.0306 one-pass).

    Document

    10-K body (~72K chars)

    Output tokens

    2,000

    Peers

    5

    Model

    Claude Haiku 4.5

    Adding five peers roughly quadruples the input to 123K tokens and lifts cost to $0.133, still cheap but no longer trivial. Multi-filing synthesis is where input volume, and therefore context window, starts to matter for model choice.

Patterns

Input tokens dominate filing-analysis cost because filings are long and outputs are short.
Anthropic models count about 3.5 characters per token versus 4 for OpenAI and Google, so the same filing is more tokens on Claude.
Compare models on cost per filing, not cost per token, to avoid tokenizer bias.
Multi-filing synthesis multiplies input volume, which is when the context window becomes a real constraint on model choice.

Try These Tools

Run the numbers next

Sources & References

Related Content

Keep the topic connected

Planning estimates only — not financial, tax, or investment advice.