SpatialRead FAQ

Cloud model's costs vary by usage and model choice. Let's walk through an example of what costs could look like. The average research paper is 20 pages long. Cloud models typically compress PDFs resulting in around 250 tokens per page. This means a 20 page PDF would be around 5000 input tokens. A response is typically 200 output tokens. If you use a model like Gemini 2.5 Flash Lite, which costs $0.10 per 1M input tokens and $0.40 per 1M output tokens, that would cost $0.0005 + $0.00008 = $0.00058/chat. Assuming you ask 50 questions a day, that's $0.029/day. That adds up to just $0.87/month. If you use one of the smartest and most expensive models, like GPT 5.1 Thinking ($1.25/$10 per 1M tokens), you could see your costs rise to $12.50/month. Most services charge a flat $10-30/month fee and generally provide access to cheap models but the advantage of Bring Your Own Keys (BYOK) is that you only pay for what you use.