A standard 1 page document (~500 words / 667 tokens) costs $0.000067 to ingest and $0.000217 to generate a comprehensive executive summary using Microsoft Phi-4 (14B).
Feed the entire 1 page document into context to extract fields, entities, or answer queries.
Ingest 1 page and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 1 page document into an equivalent length output.
| Model | Provider | Ingestion (1 page) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Microsoft Phi-4 (14B) (Current) | microsoft | $0.000067 | $0.000017 | $0.000217 | 16,384 |
| GPT-5.6 Luna | openai | $0.000128 | $0.000013 | $0.000728 | 1,050,000 |
| GPT-5.4 mini | openai | $0.00048 | $0.000048 | $0.00273 | 256,000 |
| GPT-5.4 nano | openai | $0.000128 | $0.000013 | $0.000753 | 128,000 |
| GPT-4o mini | openai | $0.000096 | $0.000048 | $0.000396 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.00066 | $0.000066 | $0.00316 | 1,000,000 |
Assuming a standard single-spaced document with ~500 words per page, a 1 page document contains approximately 500 words, which translates to roughly 667 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 1 page document consumes only 4.07% 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 $0.000217. Using 24-hour async batch API queues drops this cost to $0.000108.
If your workflow repeatedly queries or chats with this same 1 page document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.000017 per turn instead of $0.000067).