A standard 250 pages document (~125,000 words / 160,000 tokens) costs $0.40 to ingest and $0.4075 to generate a comprehensive executive summary using GPT-5.4 Workhorse.
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 |
|---|---|---|---|---|---|
| GPT-5.4 Workhorse (Current) | openai | $0.40 | $0.04 | $0.4075 | 256,000 |
| GPT-5.6 Terra | openai | $0.32 | $0.032 | $0.326 | 1,050,000 |
| o3-mini | openai | $0.176 | $0.088 | $0.1782 | 200,000 |
| o4-mini | openai | $0.176 | $0.044 | $0.1782 | 256,000 |
| o1-mini | openai | $0.176 | $0.088 | $0.1782 | 128,000 |
| Claude Sonnet 5 | anthropic | $0.33 | $0.033 | $0.335 | 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 160,000 tokens using GPT-5.4 Workhorse's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
GPT-5.4 Workhorse has a context window of 256,000 tokens. A 250 pages document consumes only 62.50% 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 $0.4075. Using 24-hour async batch API queues drops this cost to $0.2038.
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 $0.04 per turn instead of $0.40).