A standard 100 pages document (~50,000 words / 66,650 tokens) costs $0.0667 to ingest and $0.0672 to generate a comprehensive executive summary using Perplexity Sonar.
Feed the entire 100 pages document into context to extract fields, entities, or answer queries.
Ingest 100 pages and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 100 pages document into an equivalent length output.
| Model | Provider | Ingestion (100 pages) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Perplexity Sonar (Current) | perplexity | $0.0667 | $0.0167 | $0.0672 | 128,000 |
| GPT-5.6 Luna | openai | $0.0128 | $0.00128 | $0.0134 | 1,050,000 |
| GPT-5.4 mini | openai | $0.048 | $0.0048 | $0.0503 | 256,000 |
| GPT-5.4 nano | openai | $0.0128 | $0.00128 | $0.0134 | 128,000 |
| GPT-4o mini | openai | $0.0096 | $0.0048 | $0.0099 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.066 | $0.0066 | $0.0685 | 1,000,000 |
Assuming a standard single-spaced document with ~500 words per page, a 100 pages document contains approximately 50,000 words, which translates to roughly 66,650 tokens using Perplexity Sonar's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Perplexity Sonar has a context window of 128,000 tokens. A 100 pages document consumes only 52.07% 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 $0.0672. Using 24-hour async batch API queues drops this cost to $0.0336.
If your workflow repeatedly queries or chats with this same 100 pages document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.0167 per turn instead of $0.0667).