Calculator
Financial Document Token Estimator
One pass over a 10-K costs from $0.0099 on GPT-6 Luna (91,402 input tokens) to $0.896 on Claude Fable 5.2 (104,460), across 16 models.
On the documented defaults, computed by this tool's engine · the same answer as JSON
Financial document token estimator: price 10-K, 10-Q, 8-K and earnings call runs on current Claude, GPT and Gemini models, with context fit and cost.
Rates from aidevhub.io model catalog (each price verified on the vendor page), Anthropic pricing, OpenAI pricing and Google AI / Gemini pricing, checked on November 14, 2026.
01Calculator
Runs in your browser. Nothing you enter is uploaded, and no account or API key is needed.
1. Configure the document
Full main document including financial statements and notes, excluding exhibits: median of 15 filings sampled from EDGAR on 2026-10-19, about 55,710 words; the sample ran from about 23K to 273K tokens.
Length of the extraction or summary.
Same-size documents read together in one synthesis call.
0% for a document read once; caching pays on repeated prompts or re-reads.
One-pass run
91.4K
input tokens (GPT-6 Luna’s tokenizer), cheapest at $0.0099 on GPT-6 Luna, 90.6× spread to priciest
Priciest: $0.896 on Claude Fable 5.2. Output: 1.5K tok
2. Cost per model
| Model | Input tokens | Output tokens | Cache-read | One-pass cost | Synthesis cost | Context | Fits |
|---|---|---|---|---|---|---|---|
| GPT-6 Lunaopenai | 91.4K | 1.5K | 0 | $0.0099 | — | 1.05M | ✓ |
| Gemini 3.5 Flash-Litegoogle | 91.4K | 1.5K | 0 | $0.031 | — | 1.048576M | ✓ |
| Claude Haiku 5.5anthropicPrompt over 100,000 tokens: every token bills at $0.50 in / $2.50 out per 1M. | 104.5K | 1.5K | 0 | $0.056 | — | 1M | ✓ |
| Gemini 3.8 FlashgoogleFrom January 1, 2027: $1.50 in / $7.50 out per 1M. | 91.4K | 1.5K | 0 | $0.074 | — | 1.048576M | ✓ |
| GPT-5.4 Miniopenai | 91.4K | 1.5K | 0 | $0.075 | — | 400K | ✓ |
| Gemini 4 Hydrogengoogle | 91.4K | 1.5K | 0 | $0.148 | — | 1.048576M | ✓ |
| GPT-6.2 Solopenai | 91.4K | 1.5K | 0 | $0.198 | — | 1.05M | ✓ |
| Gemini 4 CarbongoogleFrom December 1, 2026: $4 in / $20 out per 1M. | 91.4K | 1.5K | 0 | $0.198 | — | 1.048576M | ✓ |
| Gemini 4 ArgongoogleFrom December 1, 2026: $4 in / $20 out per 1M. | 91.4K | 1.5K | 0 | $0.198 | — | 1.048576M | ✓ |
| Gemini 3.1 Pro Previewgoogle | 91.4K | 1.5K | 0 | $0.201 | — | 1.048576M | ✓ |
| Claude Sonnet 5.5anthropic | 104.5K | 1.5K | 0 | $0.224 | — | 1M | ✓ |
| Gemini 4 Neongoogle | 91.4K | 1.5K | 0 | $0.297 | — | 1.048576M | ✓ |
| Claude Opus 5.5anthropic | 104.5K | 1.5K | 0 | $0.448 | — | 1M | ✓ |
| GPT-5.5openai | 91.4K | 1.5K | 0 | $0.502 | — | 1.05M | ✓ |
| GPT-6.2 Astraopenai | 91.4K | 1.5K | 0 | $0.791 | — | 1.05M | ✓ |
| Claude Fable 5.2anthropic | 104.5K | 1.5K | 0 | $0.896 | — | 1M | ✓ |
Sorted cheapest first on one-pass cost. Input-token count differs slightly per provider because each tokenizer has a different char-per-token ratio.
Approximation notes
Tokenization varies per model. Estimates use published char-per-token ratios from vendor docs (Anthropic ~3.5, OpenAI ~4.0, Gemini ~4.0). For precise counts, use tiktoken (OpenAI) or Anthropic’s count_tokens endpoint. List prices verified 2026-11-14. Each call is priced on its own: when its prompt is over a model’s long-prompt threshold (Claude Haiku 5.5 over 100,000 tokens, OpenAI’s 1.05M-context models over 272K, Gemini 3.1 Pro over 200K), every token of the call bills at the higher rate, so a full 10-K can cost several times the flat price. Cache reads use each provider’s discount; cache-write surcharges (1.25× on Anthropic) are not added.
02Receipt
What the answer above ran on, how it is computed, where the data comes from, and a link that reopens it.
Inputs
archetype_id10-kcache_hit_rate0modearchetypeoutput_tokens1500peers0
The documented defaults. Change any input above and the tool recomputes.
Method
How the hub's tools are built and checked
Engine /engines/financial-document-token-estimator.js, sha256 5f5486701d75. The page, the API and MCP run the same file.
Source
aidevhub.io model catalog (each price verified on the vendor page), Anthropic pricing, OpenAI pricing and Google AI / Gemini pricing
Checked .
Permalink
aifinhub.io/financial-document-token-estimator/
The link carries the inputs you set, so it reopens this result.
03For agents
Any agent can run this calculator by URL or MCP and get the same answer as JSON: the inputs that used defaults, the result and a line to cite. The call below follows the inputs you set above. In code, import the same engine; it runs where you import it, with no request or key.
GET https://aifinhub.io/api/run/financial-document-token-estimator curl -s 'https://aifinhub.io/api/run/financial-document-token-estimator'
# Markdown instead of JSON:
curl -s 'https://aifinhub.io/api/run/financial-document-token-estimator?format=md' # MCP over Streamable HTTP, no sign-in: run_calculator
curl -s https://aifinhub.io/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"run_calculator","arguments":{"calculator":"financial-document-token-estimator","input":{}}}}' import { compute } from "https://aifinhub.io/engines/financial-document-token-estimator.js";
const result = compute(input); {
"calculator": "financial-document-token-estimator",
"title": "Financial Document Token Estimator",
"site": "AI Fin Hub",
"input": {},
"defaults_used": {
"archetype_id": "10-k",
"cache_hit_rate": 0,
"mode": "archetype",
"output_tokens": 1500,
"pasted_text": "",
"peers": 0
},
"result": [
{
"model": {
"id": "claude-fable-5-2",
"provider": "anthropic",
"name": "Claude Fable 5.2",
"inputPerMillion": 8,
"outputPerMillion": 40,
"cacheReadMultiplier": 0.025,
"cacheWriteMultiplier": 1.25,
"contextWindow": 1000000,
"charsPerToken": 3.5,
"notes": "List price for 5-minute cache writes."
},
"inputTokens": 104460,
"cacheReadTokens": 0,
"outputTokens": 1500,
"onePassCost": 0.89568,
"synthesisCost": 0.89568,
"synthesisInputTokens": 104460,
"fitsInContext": true,
"pricingNote": null
},
{
"model": {
"id": "claude-opus-5-5",
"provider": "anthropic",
"name": "Claude Opus 5.5",
"inputPerMillion": 4,
"outputPerMillion": 20,
"cacheReadMultiplier": 0.05,
"cacheWriteMultiplier": 1.25,
"contextWindow": 1000000,
"charsPerToken": 3.5,
"notes": "List price for 5-minute cache writes."
},
"inputTokens": 104460,
"cacheReadTokens": 0,
"outputTokens": 1500,
"onePassCost": 0.44784,
"synthesisCost": 0.44784,
"synthesisInputTokens": 104460,
"fitsInContext": true,
"pricingNote": null
},
{
"model": {
"id": "claude-sonnet-5-5",
"provider": "anthropic",
"name": "Claude Sonnet 5.5",
"inputPerMillion": 2,
"outputPerMillion": 10,
"cacheReadMultiplier": 0.05,
"cacheWriteMultiplier": 1.25,
"contextWindow": 1000000,
"charsPerToken": 3.5,
"notes": "List price for 5-minute cache writes."
},
"inputTokens": 104460,
"cacheReadTokens": 0,
"outputTokens": 1500,
"onePassCost": 0.22392,
"synthesisCost": 0.22392,
"synthesisInputTokens": 104460,
"fitsInContext": true,
"pricingNote": null
},
"… 13 more of 16"
],
"provenance": {
"run": "https://aifinhub.io/api/run/financial-document-token-estimator",
"page": "https://aifinhub.io/financial-document-token-estimator/",
"methodology": "https://aifinhub.io/financial-document-token-estimator/",
"contract": "https://aifinhub.io/contracts/financial-document-token-estimator.json",
"engine": "https://aifinhub.io/engines/financial-document-token-estimator.js",
"engine_sha256": "5f5486701d75621e667bdce5644faea7e02a164d8165334fdd6e3cfe9048ef03",
"build": "1a772910d31ef1740892ed0e3a065ed71e8c7406",
"prices_verified": "2026-11-14",
"prices_source": "https://aidevhub.io/api/models.json"
},
"disclaimer": "Planning estimates only — not financial, tax, or investment advice.",
"license": "https://creativecommons.org/licenses/by/4.0/",
"cite": "AI Fin Hub, Financial Document Token Estimator (engine 5f5486701d75), https://aifinhub.io/api/run/financial-document-token-estimator"
} How to use it
- Pick an archetype (10-K, 10-Q, 8-K, or earnings call) for a representative estimate, or paste the actual document text (up to 1.5 million characters).
- Read the token estimate. Pasted text uses its exact character count divided by each model's characters-per-token ratio (3.5 for Anthropic, 4.0 for the others), so it is an approximation; presets use the median length of recent filings (a 10-K main document is about 91K to 104K tokens depending on the tokenizer).
- Check the Fits column — it flags, per model, whether the document overflows that model's context window (windows range from 400K to 1.1M tokens). Documents that don't fit need chunking; see the SEC Filing Chunk Optimizer.
- Read the one-pass extraction cost across all 16 models. Raise the cache share only for prompts or documents you send repeatedly; a filing read once is a cache miss.
- Multiply per-document cost by your monthly document volume to size the bill. For batch optimization across models, pair with the Token Cost Optimizer.
Questions people ask
What documents does it support?
Four archetype presets — 10-K, 10-Q, 8-K, and earnings call transcript — or you can paste raw text (up to 1.5 million characters, enough for a full 10-K) to estimate directly. There is no file upload and no page-count input: pick an archetype for a representative estimate, or paste the actual text for a precise character-based count.
How accurate is the estimate?
The paste-text path counts your characters exactly and divides by a fixed characters-per-token ratio per provider (3.5 Anthropic, 4.0 OpenAI and Google), so the token count is an approximation; tables and long numbers usually take more tokens per character than prose. For an exact count use the provider's tokenizer or token-counting endpoint. The SEC presets are the median main-document length of recent filings we sampled from EDGAR, and real filings of the same type span roughly a tenfold range, so treat a preset number as a starting estimate, not a guarantee.
Why does token count matter for finance use?
Two reasons: (1) cost — input tokens drive LLM API cost, so you estimate before deciding to process the doc; (2) feasibility — context windows range from 400K to 1.1M tokens across the models shown, and the Fits column flags, per model, whether a document overflows. Documents that don't fit need chunking.
How do I estimate without pasting the full text?
Pick the closest archetype (10-K, 10-Q, 8-K, or earnings call). The SEC presets use the median length of recent filings' main documents, measured from EDGAR on 2026-10-19 with exhibits excluded: the 10-K preset is about 91K to 104K tokens depending on the tokenizer. There is no tokens-per-page or page-count path; for a precise number, paste the actual text and the tool counts characters divided by the model's tokenizer ratio.
Does it work for non-English filings?
The character-to-token ratios assume English prose (about 3.5–4 characters per token). Other languages tokenize differently — CJK text is denser, agglutinative languages sparser — so estimates for non-English text are rougher. There is no language selector: the ratio is fixed per model.
Related tools
- Generators SEC Filing Chunk Optimizer
Pick a filing archetype, tune chunk size and overlap, and see chunk count, embedding cost, and structural-boundary warnings across three chunking strategies.
- Calculators Token-Cost Optimizer
Compute the dollar cost of a trading research loop across Claude, GPT and Gemini: prompt length × model × retries × call volume → cost per idea and per validated trade.
- Calculators Batch vs Real-Time Cost Calculator
Jobs per day, tokens per job, model, deadline — get real-time vs batch cost side-by-side with savings estimate and batch-eligibility flag. Based on vendor-published batch pricing.
Articles
- 14 min read Long-Context Financial Question Answering: SEC Filings & RAG 2026
Long-context financial question answering over SEC filings, annual reports & earnings calls with RAG: eight LLM tasks, chunking, and 2026 benchmarks.
- 10 min read Financial QA LLM Benchmarks 2026: FinanceBench & Fin-RATE
Financial QA LLM benchmarks 2026: FinQA, FinanceBench, DocFinQA, and Fin-RATE scores, plus whole-filing read costs on the current model lineup.
- 6 min read FMP API Pricing 2026: Financial Modeling Prep Plans
FMP API pricing 2026: free Basic at 250 calls/day, then Starter $29, Premium $69, Ultimate $139 a month ($19/$49/$99 billed annually). Verified Oct 2026.