http://dwnl3pr7ombq2abcycysnlqcl7rd6lqbavnir2swapbfyzrz4e7ae4id.onion/blog/what_model_to_use.md
The financial model for AI access varies significantly: Proprietary models: Usually charge per token (input and output), with costs ranging from $0.2 to $3 per 1M tokens Open source models: Can be self-hosted or accessed through various providers, often at lower costs For heavy users, this difference can be substantial. A typical conversation might use 1,000-2,000 tokens, meaning costs can quickly accumulate with proprietary models. Also, new models using inference time compute are...