A standard 100 pages document (~50,000 words / 64,000 tokens) costs $0.32 to ingest and $0.335 to generate a comprehensive executive summary using GPT-5.5 Standard.
Feed the entire 100 pages document into context to extract fields, entities, or answer queries.
Ingest 100 pages and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 100 pages document into an equivalent length output.
| Model | Provider | Ingestion (100 pages) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| GPT-5.5 Standard (Current) | openai | $0.32 | $0.032 | $0.335 | 512,000 |
| GPT-5.6 Sol | openai | $0.32 | $0.032 | $0.335 | 1,050,000 |
| GPT-5.6 Cyber | openai | $0.80 | $0.08 | $0.8375 | 1,050,000 |
| GPT-5.5 Pro | openai | $1.92 | $0.192 | $2.01 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $1.28 | $0.128 | $1.32 | 1,000,000 |
| o3 (Reasoning Frontier) | openai | $0.64 | $0.064 | $0.66 | 1,050,000 |
Assuming a standard single-spaced document with ~500 words per page, a 100 pages document contains approximately 50,000 words, which translates to roughly 64,000 tokens using GPT-5.5 Standard's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
GPT-5.5 Standard has a context window of 512,000 tokens. A 100 pages document consumes only 12.50% 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 $0.335. Using 24-hour async batch API queues drops this cost to $0.1675.
If your workflow repeatedly queries or chats with this same 100 pages document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.032 per turn instead of $0.32).