Show HN: AI Model Token Cost and Context Window Estimator

A developer released a Show HN tool that estimates token counts, context-window fit, and API costs across multiple large language models, including a side-by-side comparison matrix of context limits and per-1M-token input and output pricing. The estimator accepts TXT, JSON, MD, CSV, or PDF files, reports usage against a 128,000-token context limit, and projects costs for a single API request and a 100,000-request production batch. The tool targets teams planning large-scale prompt deployments who need to compare flagship and lightweight LLMs on cost and capacity before committing.

0 Words: 0 TXT, JSON, MD, CSV, or PDF files here or click to browse 0 / 128,000 tokens 0.0% Your prompt comfortably fits within this model's capacity limit. Production Multi-Run Batch Estimator Project total operational cost when deploying this prompt configuration at scale. Side-by-Side Model Comparison Matrix Comparing current token metrics across flagship and lightweight LLMs. | Model | Provider | Context Limit | Input / 1M | Output / 1M | 1 API Request | 100k Production Batch | |---|---|---|---|---|---|---|