The Gemini Decisions API allows developers to make fast, probabilistic choices across text, images, audio, video, and PDFs in a single pass, providing confidence scores for multiple questions. It can process up to 1,000 independent questions per request and returns probabilities and confidence scores in 150-250 ms end-to-end latency at $0.10 per 1M input tokens. The API is priced at $0.10 per 1M input tokens and $0 for output tokens, with no output-token charges, variable thinking-token bills, or separate audio transcription and OCR costs. AI summary
Firehose
Filtered to tagged “NLP” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 63continual learning 22AI 19agentic coding 17open-weight models 14reinforcement learning 12AI agents 11AI safety 8datasette 7machine learning 7natural language processing 7benchmarks 6language models 6Nvidia 6Reinforcement learning 6robotics 6deep learning 5Diffusion models 5large language models 5open-source 5Agentic AI 4AI ethics 4AI Gateway 4Databricks 4decision models 4Gemini 4general 4Jensen Huang 4Recursive self-improvement 4software development 4