A standard 500 pages document (~250,000 words / 333,250 tokens) costs $0.1466 to ingest and $0.1477 to generate a comprehensive executive summary using Devstral 2 (2512) (OpenRouter).
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 |
|---|---|---|---|---|---|
| Devstral 2 (2512) (OpenRouter) (Current) | mistral | $0.1466 | $0.0147 | $0.1477 | 262,144 |
| GPT-5.3 Codex | openai | $0.56 | $0.056 | $0.567 | 256,000 |
| DeepSeek Coder V2.5 | deepseek | $0.0467 | $0.004666 | $0.0468 | 128,000 |
| Codestral 2501 | mistral | $0.10 | $0.009998 | $0.1004 | 256,000 |
| Grok Build 0.1 | xai | $0.3333 | $0.0667 | $0.3343 | 256,000 |
| Qwen 2.5 Coder 32B | qwen | $0.0667 | $0.006665 | $0.067 | 128,000 |
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 Devstral 2 (2512) (OpenRouter)'s tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
Devstral 2 (2512) (OpenRouter) has a context window of 262,144 tokens. A 500 pages document consumes only 127.12% 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 $0.1477. Using 24-hour async batch API queues drops this cost to $0.0739.
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 $0.0147 per turn instead of $0.1466).