A standard 250 pages document (~125,000 words / 166,625 tokens) costs $0.0167 to ingest and $0.0168 to generate a comprehensive executive summary using Microsoft Phi-4 (14B).
Quick answer
A 250 pages document is modeled as 125,000 words or 166,625 tokens. With Microsoft Phi-4 (14B), ingestion costs $0.0167; a 500-token executive summary brings the modeled total to $0.0168.
Method & trust
The page uses approximately 500 words per page, estimates tokens with the selected model tokenizer, and prices input plus a 500-token summary at the model's listed rates. OCR, tables, and formatting can increase the actual count.
Feed the entire 250 pages document into context to extract fields, entities, or answer queries.
Ingest 250 pages and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 250 pages document into an equivalent length output.
| Model | Provider | Ingestion (250 pages) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Microsoft Phi-4 (14B) (Current) | microsoft | $0.0167 | $0.004166 | $0.0168 | 16,384 |
| GPT-5.6 Luna | openai | $0.032 | $0.0032 | $0.0326 | 1,050,000 |
| GPT-5.4 mini | openai | $0.12 | $0.012 | $0.1223 | 256,000 |
| GPT-5.4 nano | openai | $0.032 | $0.0032 | $0.0326 | 128,000 |
| GPT-4o mini | openai | $0.024 | $0.012 | $0.0243 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.165 | $0.0165 | $0.1675 | 1,000,000 |
Assuming a standard single-spaced document with ~500 words per page, a 250 pages document contains approximately 125,000 words, which translates to roughly 166,625 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 250 pages document consumes only 1017.00% 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 $0.0168. Using 24-hour async batch API queues drops this cost to $0.008406.
If your workflow repeatedly queries or chats with this same 250 pages document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.004166 per turn instead of $0.0167).