A standard 500 pages document (~250,000 words / 333,250 tokens) costs $0.0467 to ingest and $0.0467 to generate a comprehensive executive summary using Yi-Lightning (01.AI).
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 |
|---|---|---|---|---|---|
| Yi-Lightning (01.AI) (Current) | 01ai | $0.0467 | $0.0117 | $0.0467 | 16,384 |
| GPT-5.6 Luna | openai | $0.064 | $0.0064 | $0.0646 | 1,050,000 |
| GPT-5.4 mini | openai | $0.24 | $0.024 | $0.2423 | 256,000 |
| GPT-5.4 nano | openai | $0.064 | $0.0064 | $0.0646 | 128,000 |
| GPT-4o mini | openai | $0.048 | $0.024 | $0.0483 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.33 | $0.033 | $0.3325 | 1,000,000 |
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 Yi-Lightning (01.AI)'s tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Yi-Lightning (01.AI) has a context window of 16,384 tokens. A 500 pages document consumes only 2034.00% 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 $0.0467. Using 24-hour async batch API queues drops this cost to $0.0234.
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 $0.0117 per turn instead of $0.0467).