A standard 500 pages document (~250,000 words / 333,250 tokens) costs $0.20 to ingest and $0.2009 to generate a comprehensive executive summary using Databricks DBRX Instruct.
Feed the entire 500 pages document into context to extract fields, entities, or answer queries.
Ingest 500 pages and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 500 pages document into an equivalent length output.
| Model | Provider | Ingestion (500 pages) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Databricks DBRX Instruct (Current) | databricks | $0.20 | $0.05 | $0.2009 | 32,768 |
| GPT-5.6 Terra | openai | $0.64 | $0.064 | $0.646 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $0.80 | $0.08 | $0.8075 | 256,000 |
| o3-mini | openai | $0.352 | $0.176 | $0.3542 | 200,000 |
| o4-mini | openai | $0.352 | $0.088 | $0.3542 | 256,000 |
| o1-mini | openai | $0.352 | $0.176 | $0.3542 | 128,000 |
Assuming a standard single-spaced document with ~500 words per page, a 500 pages document contains approximately 250,000 words, which translates to roughly 333,250 tokens using Databricks DBRX Instruct's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Databricks DBRX Instruct has a context window of 32,768 tokens. A 500 pages document consumes only 1017.00% 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 $0.2009. Using 24-hour async batch API queues drops this cost to $0.1004.
If your workflow repeatedly queries or chats with this same 500 pages document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.05 per turn instead of $0.20).