A standard 5 pages document (~2,500 words / 3,333 tokens) costs $0.005833 to ingest and $0.007583 to generate a comprehensive executive summary using Llama 3.1 405B Instruct.
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 |
|---|---|---|---|---|---|
| Llama 3.1 405B Instruct (Current) | meta | $0.005833 | $0.001458 | $0.007583 | 128,000 |
| GPT-5.6 Sol | openai | $0.016 | $0.0016 | $0.031 | 1,050,000 |
| GPT-5.6 Cyber | openai | $0.04 | $0.004 | $0.0775 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.016 | $0.0016 | $0.031 | 512,000 |
| GPT-5.5 Pro | openai | $0.096 | $0.0096 | $0.186 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $0.064 | $0.0064 | $0.104 | 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 Llama 3.1 405B Instruct's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Llama 3.1 405B Instruct has a context window of 128,000 tokens. A 5 pages document consumes only 2.60% 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 $0.007583. Using 24-hour async batch API queues drops this cost to $0.003791.
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 $0.001458 per turn instead of $0.005833).