A standard 5 pages document (~2,500 words / 3,333 tokens) costs $0.000333 to ingest and $0.000483 to generate a comprehensive executive summary using Microsoft Phi-4 (14B).
Feed the entire 5 pages document into context to extract fields, entities, or answer queries.
Ingest 5 pages and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 5 pages document into an equivalent length output.
| Model | Provider | Ingestion (5 pages) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Microsoft Phi-4 (14B) (Current) | microsoft | $0.000333 | $0.000083 | $0.000483 | 16,384 |
| GPT-5.6 Luna | openai | $0.00064 | $0.000064 | $0.00124 | 1,050,000 |
| GPT-5.4 mini | openai | $0.0024 | $0.00024 | $0.00465 | 256,000 |
| GPT-5.4 nano | openai | $0.00064 | $0.000064 | $0.001265 | 128,000 |
| GPT-4o mini | openai | $0.00048 | $0.00024 | $0.00078 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.0033 | $0.00033 | $0.0058 | 1,000,000 |
Assuming a standard single-spaced document with ~500 words per page, a 5 pages document contains approximately 2,500 words, which translates to roughly 3,333 tokens using Microsoft Phi-4 (14B)'s tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Microsoft Phi-4 (14B) has a context window of 16,384 tokens. A 5 pages document consumes only 20.34% of its total window, easily fitting in a single prompt without requiring chunking or vector search.
Ingesting the document and outputting a concise 500-token executive summary costs $0.000483. Using 24-hour async batch API queues drops this cost to $0.000242.
If your workflow repeatedly queries or chats with this same 5 pages document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.000083 per turn instead of $0.000333).