A standard 250 pages document (~125,000 words / 166,625 tokens) costs $0.025 to ingest and $0.0252 to generate a comprehensive executive summary using Llama 4 Scout (109B MoE).
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 |
|---|---|---|---|---|---|
| Llama 4 Scout (109B MoE) (Current) | meta | $0.025 | $0.006248 | $0.0252 | 10,000,000 |
| GPT-5.6 Terra | openai | $0.32 | $0.032 | $0.326 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $0.40 | $0.04 | $0.4075 | 256,000 |
| 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 |
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 Llama 4 Scout (109B MoE)'s tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Llama 4 Scout (109B MoE) has a context window of 10,000,000 tokens. A 250 pages document consumes only 1.67% 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 $0.0252. Using 24-hour async batch API queues drops this cost to $0.0126.
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 $0.006248 per turn instead of $0.025).