A standard 1 page document (~500 words / 667 tokens) costs $0.000293 to ingest and $0.001393 to generate a comprehensive executive summary using Devstral 2 (2512) (OpenRouter).
Quick answer
A 1 page document is modeled as 500 words or 667 tokens. With Devstral 2 (2512) (OpenRouter), ingestion costs $0.000293; a 500-token executive summary brings the modeled total to $0.001393.
Method & trust
The page uses approximately 500 words per page, estimates tokens with the selected model tokenizer, and prices input plus a 500-token summary at the model's listed rates. OCR, tables, and formatting can increase the actual count.
Feed the entire 1 page document into context to extract fields, entities, or answer queries.
Ingest 1 page and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 1 page document into an equivalent length output.
| Model | Provider | Ingestion (1 page) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| Devstral 2 (2512) (OpenRouter) (Current) | mistral | $0.000293 | $0.000029 | $0.001393 | 262,144 |
| GPT-5.3 Codex | openai | $0.00112 | $0.000112 | $0.00812 | 256,000 |
| DeepSeek Coder V2.5 | deepseek | $0.000093 | $0.0000093 | $0.000233 | 128,000 |
| Codestral 2501 | mistral | $0.0002 | $0.000020 | $0.00065 | 256,000 |
| Grok Build 0.1 | xai | $0.000667 | $0.000133 | $0.001667 | 256,000 |
| Qwen 2.5 Coder 32B | qwen | $0.000133 | $0.000013 | $0.000433 | 128,000 |
Assuming a standard single-spaced document with ~500 words per page, a 1 page document contains approximately 500 words, which translates to roughly 667 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 1 page document consumes only 0.25% 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 $0.001393. Using 24-hour async batch API queues drops this cost to $0.000697.
If your workflow repeatedly queries or chats with this same 1 page document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.000029 per turn instead of $0.000293).