| "I built https://tokencost.is to solve a recurring headache: manually scraping dozens of provider pages just to estimate API spend for my agentic workflows. My goal was a neutral, minimalist utility in the vein of Time.is. We now track 44 models—including OpenAI, Anthropic, Google, DeepSeek, Mistral, and Cohere—with hourly updates. Key Features: Real-Time Latency: We track TTFT benchmarks (e.g., Llama 3.1 at 28ms) alongside pricing. Price Deltas: We track 24h market shifts; look for the ↑↓ indicators in the table to see how the 'AI Price War' is moving. Multimodal Calculator: Handles Text, Audio, and Video tokens in a single UI. 100% Neutral: No affiliate bias or listing fees. Just raw data scraped hourly. I’m not a developer by trade, so I used an agentic workflow to build the backend and scrapers. I found that being the 'product owner' rather than the 'coder' actually helped me focus on the data integrity and the specific multimodal features I needed for my own work. I'd love to hear what other 2026 models or enterprise benchmarks the community would like to see indexed next!" |
If possible, it would be useful to also see which models can be fine-tuned, if the information is available.
PS. You might want to add Inception labs (https://www.inceptionlabs.ai/models#pricing)