Google's Gemini Decisions API returns yes/no, MCQ and rubric calls in 150-250ms
_philschmid · x · 2026-11-12
Google launched the Gemini Decisions API, powered by the new Gemini Decision 1 model, built for closed-set choices instead of token-by-token text generation.
- Three decision types: yes/no, multiple choice (up to 255 options), and rubric scoring
- Inputs: text, images, audio, video, PDFs; up to 1,000 questions per request; 256K context
- 150-250ms end-to-end latency with a confidence score on every answer
- Pricing: $0.10 per 1M input tokens, $0 for output — roughly 5x cheaper than Flash-Lite
Google says it leads several benchmark evals with the lowest calibration error, and internal teams like Stitch Rapid already use it to design full product flows in seconds.
More from coding & agent
- Choosing the Right Codex Model and Effort Level for Research Tasks, Plus an Open-Source Skill — udmrzn · 2026-11-12
- Who reads the queries your agent writes? A diagram of agentic search data flows — adnan_hashmi · 2026-11-12
- Hackathon project lets AI agents spend company money, but only within CFO-approved limits — kleffew94 · 2026-11-12
- In real orgs the model is rarely the problem — the context it gets is, says Salesforce engineer — msrivastav13 · 2026-11-12
- Salesforce Winter '27 adds AiAgentDefinition metadata for versioned agent deployments — msrivastav13 · 2026-11-12
- Solo dev builds zombie horde level with Tripo P2.0, Fable and new Kaigen engine — gdechichi · 2026-11-12