AKF Diligence Toolbook — API Cost Estimates

Per-engagement token and cost reference · Anthropic API direct billing · September 2026

anthropic API
LARGE DOC 80–100 page PDF  ≈  50,000 tokens
TRANSCRIPT 3-hour session  ≈  30,000 tokens
DOCS COUNT 3 large documents
TRANS COUNT 2 transcripts
TOTAL UPLOAD 210,000 tokens (≈ 840 pages combined)
CACHING Active on Tools 04–07 after first call
#
Tool
Input tokens
No docs
Heavy run
01
Biz Dev Call Prep
Web search capped at 3 queries · no documents, no caching
claude-opus-4-8
~8,000 prompt
+ web results
~8,000 out
n/a
$0.24 (≈$0.43 if a retry is needed)
02
SOW Generator
Core builder (sections, pricing, Word/PDF export) is 100% local — no API calls at all
no API
$0.00
$0.00
02
↳ optional: Import from call transcript
One-time analysis of a pasted transcript into suggested SOW bullets
claude-opus-4-8
~30,000 transcript
~2,500 out
$0.22
02
↳ optional: Generate Email
Drafts the outreach email from the SOW content (+ transcript, if present)
claude-opus-4-8
~1,200–31,700 in
~900 out
$0.03
$0.22
03
Target Intel
Web search + architecture brief · 1 typical doc
claude-sonnet-4-5
~4,800 prompt
~50,000 doc
~4,000 out
$0.07
$0.22
04
Diligence Coach — single question
No API call unless Target Context is set · first call (docs uncached) · subsequent calls (docs cached)
claude-haiku-4-5
~1,400 prompt
~210,000 docs
~1,000 out
↻ cached after Q1
$0.00
$0.22 → $0.03
04
Diligence Coach — full 133 questions
Requires Target Context · 1 cache-miss + 132 cache-hits on documents
claude-haiku-4-5
133 × 2,400 in
133 × 1,000 out
210k docs cached ×132
$0.00
$3.83
05
TDD Scorecard
3 large docs + 2 transcripts · 8-domain framework embedded
claude-sonnet-4-6
~4,100 prompt
~210,000 docs
~4,000 out
$0.12
$1.17
06
RepGen Scorer
3 large docs + 2 transcripts · ~133 questions + rubrics · model is user-selectable
Opus 4.5 / 4.8 Sonnet 5
~14,000 questions
~2,400 prompt
~210,000 docs
~8,000 out
$0.28
$1.33
07
Report Generator
SOW + RepGen HTML export (~25k) + Scorecard HTML (~8k)
claude-sonnet-4-6
~42,800 total in
~8,000 out
$0.41
Lean engagement
$0.71
Biz Dev Call Prep, SOW Generator (builder only, no AI features), Target Intel, Diligence Coach with no Target Context, Scorecard, RepGen — minimal or no uploaded documents
Heavy engagement
$7.64
All seven tools, SOW Generator's transcript import + email generation, all 133 coaching questions, 3 large docs + 2 × 3-hour transcripts uploaded to each tool
claude-haiku-4-5
Input$1.00 / M tokens
Output$5.00 / M tokens
Cache read$0.10 / M tokens
claude-sonnet-4-5
Input$3.00 / M tokens
Output$15.00 / M tokens
Cache read$0.30 / M tokens
claude-opus-4-5 / 4-8
Input$5.00 / M tokens
Output$25.00 / M tokens
Cache read$0.50 / M tokens

Token estimates: 1 token ≈ 4 characters of English text. A 3-hour session transcript at ~150 words/min ≈ 27,000 tokens. An 80-page PDF ≈ 40,000–60,000 tokens depending on density.

Prompt caching (Tools 04–07): Uploaded documents are sent first in the API message with a cache marker. After the first call in a session, document tokens are re-read at ~10% of input price. Cache TTL is 5 minutes — brief pauses between questions will not miss the cache; extended breaks may.

Diligence Coach note: As of this version, the API is only called once Target Context is added — clicking a question with no context shows it directly from the local question bank at no cost. The $3.83 full-run figure applies only once context is set and all 133 questions are generated fresh with documents attached. Cached localStorage responses from prior sessions are free — typical cost per engagement is materially lower.

Biz Dev Call Prep note: Web search is hard-capped at 3 queries per run (enforced by the API, not just prompted). If the first pass runs out of budget before finishing, one automatic retry occurs with a larger token budget and no further search — worst case ≈$0.43 instead of the typical $0.24.

SOW Generator note: The core builder — sections, sessions, pricing, phases, Word/PDF export — makes no API calls at all. Only the optional "Import from call transcript" and "Generate Email" features call the API, each gated behind its own cost estimate and confirmation prompt before running.

Observed vs estimated: A TDD Scorecard run with 3 large docs + 2 transcripts observed at $0.95 — consistent with the $1.17 estimate (variation due to actual vs assumed document sizes and output length).

Spend control: Set a monthly limit at console.anthropic.com → Settings → Billing → Spend limits.