Google launches Gemini Decisions API: scores 1,000 questions per pass, output tokens free
dean_rie · x · 2026-11-12
Sundar Pichai announced the Gemini Decisions API, powered by the new Gemini Decision 1 model in Google AI Studio. Instead of generating text token by token, it's built for closed-set choice scoring — up to 1,000 questions across text, images, audio, video and PDFs in a single pass.
Key details:
- Three decision types: yes/no, multiple choice (up to 255 options), and rubric scoring
- Pricing: $0.10/1M input tokens with $0 billed for output tokens (5x cheaper than Flash-Lite)
- Leads several benchmark evals with the lowest calibration error
- Google teams are already building on it; Stitch Rapid demoed designing a full product flow in seconds
Related event: Google Launches Gemini Decisions API with Decision 1 Model(22 posts)→
More from coding & agent
- Gemini API Managed Agents now support self-hosted sandboxes, incl. Vercel — steren · 2026-11-12
- Rayline launches ARC, a per-turn model router claiming 90% cost cuts — testingcatalog · 2026-11-12
- Karpathy's llm-wiki: a pattern for building personal knowledge bases with LLM agents — stochasticchasm · 2026-11-12
- Agent self-improvement with frozen weights: failure traces add just 4pp, blind search gets 60% — burny_tech · 2026-11-12
- Microsoft on agentic schedulers: LLM proposes, deterministic code validates — WirelessLife · 2026-11-12
- Visual block scripting drives an AI opponent in a classic arcade game — ezshine · 2026-11-12