Google ships Gemini Decisions API: 1,000 questions per request at 150-250ms, $0.10 per 1M tokens
_philschmid · x · 2026-11-12
Google launched the Gemini Decisions API alongside a new model, Gemini Decision 1, built for yes/no, multiple-choice, and rubric questions. Philipp Schmid, who helped design and evaluate the API, says the project started organically inside Google DeepMind: an internal prototype was picked up rapidly by teams across Google, and a small research-engineering-product team shipped model and API together within six weeks.
Key specs:
- Accepts text, images, audio, video, and PDFs as input
- Up to 1,000 questions per request, 256k context
- 150-250 ms end-to-end latency
- $0.10 per 1M input tokens, $0 output
- Confidence score on every answer
Related event: Google Launches Gemini Decisions API with Gemini Decision 1 Model(22 posts)→
More from Models
- Claude Fable 5.2 tops Agent Arena at +30.4%, 1.5x the gain of runner-up Opus 5.5 — daniel_mac8 · 2026-11-12
- Polymarket Puts Only ~40% Odds on Next Gemini Flash (3.9+) Shipping by Year-End — Polymarket · 2026-11-12
- Agent Arena update: Muse Ember (Max) debuts at #25, tied with Muse Wonder — arena · 2026-11-12
- Blood on the Clocktower benchmark: Kimi K3.1 Pro tops open models, just below GPT 5.5 — eliebakouch · 2026-11-12
- Replicating all 9 weight-space programming experiments: big wins, one miss — burny_tech · 2026-11-12
- Open-source Iris-Z unifies image generation and depth in one backbone, beating MoGe-3 — victormustar · 2026-11-12