Google launches Gemini Decisions API, a fully multimodal decision model
Simon Willison · rss · 2026-11-12
Google joins Jev and OpenAI in the decision-model category with Gemini Decision 1. It supports the same three question types (yes/no, choice, rubric-scoring) and even reuses Jev's term "Noul" for yes/no questions.
Pricing: Same as GPT-6 Luna — $0.10 per million input tokens, output free. Jev remains cheapest at $0.042/M.
Modalities: Jev is text/JSON only; OpenAI handles text and images; Gemini Decision 1 is fully multimodal — text, images, audio, video, and PDFs.
Simon Willison tested it on his Yonkers stomping-robot video: Jev and OpenAI return 1.0/0.0 for yes/no, while Gemini outputs calibrated probabilities — robot 0.92, usa 0.92, dragon 0.05, france 0.08.
More from Models
- Models invent their own filler tokens during RL training — code_star · 2026-11-13
- Google Search reportedly gets massive Gemini 4 Hydrogen upgrade with in-search simulations — AI_Andrew · 2026-11-13
- $500 bounty offered for pre-2020 human text flagged as AI by Pangram — gleech · 2026-11-13
- $100-$200/mo frontier AI subscription tiers: "this shapes the future economy" — vedantmisra · 2026-11-13
- QuixiAI calls out Edge0 for cherry-picked benchmark chart that drops Claude where it loses — QuixiAI · 2026-11-13
- Grok goes viral for picking Jensen Huang's wife in AI-generated 'who would you choose' prompt — enggirlfriend · 2026-11-13