A standard 50 pages document (~25,000 words / 33,325 tokens) costs $0.0667 to ingest and $0.0707 to generate a comprehensive executive summary using AI21 Jamba 1.5 Large.
Feed the entire 50 pages document into context to extract fields, entities, or answer queries.
Ingest 50 pages and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 50 pages document into an equivalent length output.
| Model | Provider | Ingestion (50 pages) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| AI21 Jamba 1.5 Large (Current) | ai21 | $0.0667 | $0.0167 | $0.0707 | 256,000 |
| GPT-5.6 Sol | openai | $0.16 | $0.016 | $0.175 | 1,050,000 |
| GPT-5.6 Cyber | openai | $0.40 | $0.04 | $0.4375 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.16 | $0.016 | $0.175 | 512,000 |
| GPT-5.5 Pro | openai | $0.96 | $0.096 | $1.05 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $0.64 | $0.064 | $0.68 | 1,000,000 |
Assuming a standard single-spaced document with ~500 words per page, a 50 pages document contains approximately 25,000 words, which translates to roughly 33,325 tokens using AI21 Jamba 1.5 Large's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
AI21 Jamba 1.5 Large has a context window of 256,000 tokens. A 50 pages document consumes only 13.02% 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 $0.0707. Using 24-hour async batch API queues drops this cost to $0.0353.
If your workflow repeatedly queries or chats with this same 50 pages document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.0167 per turn instead of $0.0667).