Workload cost scenario

Document Summarization API Cost Calculator

Estimate the cost of summarizing long documents with a large input-to-output ratio across tracked AI models.

Document, legal operations, and knowledge-management teams.

Editable assumptions

Model the workload

Change the inputs to recalculate every compatible model.

Lowest tracked estimate
$55.50

Gemini 2.5 Flash-Lite for the current assumptions

Lowest cost does not mean best model. Test output quality, latency, retries, and reliability on your own workload.

Cost comparison

Estimated monthly cost by model

Comparing 22 models that fit the initial input length.

ModelProviderInput costOutput costMonthly estimateContext usage
Gemini 2.5 Flash-LiteGoogle$45.50$10.00$55.504.8%
DeepSeek V4 Flash non-thinkingDeepSeek$63.14$7.00$70.145.0%
GPT-4o miniOpenAI$71.25$15.00$86.2539.1%
gpt-5.4-nanoOpenAI$91.00$31.25$122.2512.5%
Gemini 3.5 Live Translate PreviewGoogle$113.75$37.50$151.2538.1%
Gemini 3.1 Flash-LiteGoogle$113.75$37.50$151.254.8%
Gemini 2.5 FlashGoogle$136.50$62.50$199.004.8%
deepseek-v4-proDeepSeek$195.93$21.75$217.685.0%
Gemini 3 Flash PreviewGoogle$227.50$75.00$302.504.8%
gpt-5.4-miniOpenAI$341.25$112.50$453.7512.5%
Claude Haiku 4.5Anthropic$455.00$125.00$580.0025.0%
gpt-5.6-lunaOpenAI$455.00$150.00$605.004.8%
Gemini 2.5 ProGoogle$568.75$250.00$818.754.8%
Gemini 3.5 FlashGoogle$682.50$225.00$907.504.8%
Claude Sonnet 5Anthropic$910.00$250.00$1,160.005.0%
Gemini 3.1 Pro PreviewGoogle$910.00$300.00$1,210.004.8%
GPT-4oOpenAI$1,187.50$250.00$1,437.5039.1%
gpt-5.6-terraOpenAI$1,137.50$375.00$1,512.504.8%
Claude Sonnet 4.6Anthropic$1,365.00$375.00$1,740.005.0%
Claude Opus 4.8Anthropic$2,275.00$625.00$2,900.005.0%
gpt-5.6-solOpenAI$2,275.00$750.00$3,025.004.8%
Claude Fable 5Anthropic$5,000.00$1,250.00$6,250.005.0%
Why this scenario matters

Document summarization cost drivers

Document summarization is input-heavy, while requested summary length and repeated boilerplate determine how much output and cache pricing matter.

StackLens checklist

What to measure

  • Sample real document lengths instead of relying only on an average.
  • Set summary-length targets by document type.
  • Check whether map-reduce summarization adds extra calls.

Estimate boundary: OCR, file ingestion, multimodal document processing, and multi-pass summarization are not included.

View pricing sources

OpenAI model pricingHigh confidenceChecked 2026-07-13

Tracked prices for included OpenAI models are checked against official provider documentation.

Anthropic model pricingHigh confidenceChecked 2026-07-12

Tracked prices for included Anthropic models are checked against official provider documentation.

Google model pricingHigh confidenceChecked 2026-07-14

Tracked prices for included Google models are checked against official provider documentation.

DeepSeek model pricingHigh confidenceChecked 2026-07-12

Tracked prices for included DeepSeek models are checked against official provider documentation.

Anthropic model pricingHigh confidenceChecked 2026-07-14

Tracked prices for included Anthropic models are checked against official provider documentation.