A standard 250 pages document (~125,000 words / 166,625 tokens) costs $0.0833 to ingest and $0.0841 to generate a comprehensive executive summary using Mistral Large 3.
Feed the entire 250 pages document into context to extract fields, entities, or answer queries.
Ingest 250 pages and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 250 pages document into an equivalent length output.
| Model | Provider | Ingestion (250 pages) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Mistral Large 3 (Current) | mistral | $0.0833 | $0.008331 | $0.0841 | 1,000,000 |
| GPT-5.6 Sol | openai | $0.80 | $0.08 | $0.815 | 1,050,000 |
| GPT-5.6 Cyber | openai | $2.00 | $0.20 | $2.038 | 1,050,000 |
| GPT-5.5 Standard | openai | $0.80 | $0.08 | $0.815 | 512,000 |
| GPT-5.5 Pro | openai | $4.80 | $0.48 | $4.89 | 512,000 |
| o3-pro (Frontier Reasoning) | openai | $3.20 | $0.32 | $3.24 | 1,000,000 |
Assuming a standard single-spaced document with ~500 words per page, a 250 pages document contains approximately 125,000 words, which translates to roughly 166,625 tokens using Mistral Large 3's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Mistral Large 3 has a context window of 1,000,000 tokens. A 250 pages document consumes only 16.66% 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 $0.0841. Using 24-hour async batch API queues drops this cost to $0.042.
If your workflow repeatedly queries or chats with this same 250 pages document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.008331 per turn instead of $0.0833).