A standard 1 page document (~500 words / 667 tokens) costs $0.0003 to ingest and $0.000925 to generate a comprehensive executive summary using Llama 4 Maverick (400B MoE).
Feed the entire 1 page document into context to extract fields, entities, or answer queries.
Ingest 1 page and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 1 page document into an equivalent length output.
| Model | Provider | Ingestion (1 page) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Llama 4 Maverick (400B MoE) (Current) | meta | $0.0003 | $0.000075 | $0.000925 | 1,000,000 |
| GPT-5.6 Sol | openai | $0.0032 | $0.00032 | $0.0182 | 1,050,000 |
| GPT-5.6 Cyber | openai | $0.008 | $0.0008 | $0.0455 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.0032 | $0.00032 | $0.0182 | 512,000 |
| GPT-5.5 Pro | openai | $0.0192 | $0.00192 | $0.1092 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $0.0128 | $0.00128 | $0.0528 | 1,000,000 |
Assuming a standard single-spaced document with ~500 words per page, a 1 page document contains approximately 500 words, which translates to roughly 667 tokens using Llama 4 Maverick (400B MoE)'s tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Llama 4 Maverick (400B MoE) has a context window of 1,000,000 tokens. A 1 page document consumes only 0.07% 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 $0.000925. Using 24-hour async batch API queues drops this cost to $0.000463.
If your workflow repeatedly queries or chats with this same 1 page document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.000075 per turn instead of $0.0003).