EmbeddingGemma 2: an open, lightweight multimodal embedding model
deepmind.google·6d ago
AI Engineering
Hacker News·Aug 2·5 min read
Show HN: CostPerPrompt – Live AI API pricing and real-workload cost calculators
TL;DR
CostPerPrompt is a new tool that provides live pricing for over 232 AI models, allowing users to calculate the monthly costs of their AI workloads based on token usage. This resource helps developers and researchers make informed decisions about which models to use based on real-time pricing data.
✦ Why It Matters
Use CostPerPrompt today to accurately estimate your AI project costs and optimize your model selection.
Key Takeaways
- Utilize CostPerPrompt for real-time AI pricing insights.
- Factor in prompt caching to reduce input costs significantly.
- Consider batch processing to lower overall expenses by 50%.
- Review pricing for multiple models to find the best fit for your needs.
How It Works
CostPerPrompt calculates costs based on token usage, where a token is roughly three-quarters of a word. Users pay separately for input and output tokens, with output typically being more expensive.
The tool incorporates discounts for repeated inputs and batch processing, providing a more accurate cost estimate.