A standard 10 pages document (~5,000 words / 6,665 tokens) costs $0.002 to ingest and $0.00245 to generate a comprehensive executive summary using Codestral 2501.
Feed the entire 10 pages document into context to extract fields, entities, or answer queries.
Ingest 10 pages and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 10 pages document into an equivalent length output.
| Model | Provider | Ingestion (10 pages) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Codestral 2501 (Current) | mistral | $0.002 | $0.0002 | $0.00245 | 256,000 |
| GPT-5.3 Codex | openai | $0.0112 | $0.00112 | $0.0182 | 256,000 |
| DeepSeek Coder V2.5 | deepseek | $0.000933 | $0.000093 | $0.001073 | 128,000 |
| Grok Build 0.1 | xai | $0.006665 | $0.001333 | $0.007665 | 256,000 |
| Qwen 2.5 Coder 32B | qwen | $0.001333 | $0.000133 | $0.001633 | 128,000 |
| DeepInfra — Qwen 2.5 Coder 32B | deepinfra | $0.000533 | $0.000133 | $0.000653 | 128,000 |
Assuming a standard single-spaced document with ~500 words per page, a 10 pages document contains approximately 5,000 words, which translates to roughly 6,665 tokens using Codestral 2501's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Codestral 2501 has a context window of 256,000 tokens. A 10 pages document consumes only 2.60% 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 $0.00245. Using 24-hour async batch API queues drops this cost to $0.001225.
If your workflow repeatedly queries or chats with this same 10 pages document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.0002 per turn instead of $0.002).