Latest / Frontier models and safety
Google releases Gemini Decision 1, a model that scores up to 1,000 questions in one pass
See how this story connectsGoogle introduced the Gemini Decisions API, powered by its new Gemini Decision 1 model (gemini-decision-1), available through the Gemini API in Google AI Studio. The API evaluates up to 1,000 yes/no, multiple-choice and rubric-scoring questions in one pass over text, images, audio, video and PDFs of up to 256K tokens, and returns probabilities and confidence scores in 150 to 250 ms end to end. It costs $0.10 per 1M input tokens with no output tokens billed, and Google says it already uses it for model routing in Gemini Notebook and for safety checks on MCP tools in Search.
Why it matters
Developers building agents get a priced Google endpoint for routing, grading and policy checks that returns a probability and confidence score for each question instead of generated text.
- When
- 11 Nov 2026
- ID
WTA-N-2026-0856- Where
- United States
- Who
- Google, Google DeepMind
- Topics
- Model releases, Frontier models, AI agents
Summary written with AI by wheresthe.ai, from Google and the reporting credited above. Checked against the source on 11 Nov 2026.
Source copy: saved on 11 Nov 2026 to check this story and not republished, because the text belongs to its publisher. Also held by the Internet Archive.
Cite this story
WTA-N-2026-0856: “Google releases Gemini Decision 1, a model that scores up to 1,000 questions in one pass.” wheresthe.ai, 11 Nov 2026. https://wheresthe.ai/d/us-google-releases-gemini-decision-1-a-model-that-scores-up-to-1-2026-11/ (source: Google).
Spotted an error? Email [email protected].