Google launches the Gemini Decisions API: Gemini Decision 1 answers up to 1,000 closed-set questions in one pass at $0.10 per million input tokens, with no output billed
A new endpoint built only for picking from fixed options: instead of generating answer text, it scores each option with a probability. What it does, how fast and cheap it is, and how Google uses it.
// Key points
- One request takes a single multimodal input (text, images, audio, video and PDFs, up to 256K tokens) plus up to 1,000 independent questions, as yes/no, multiple choice (2 to 255 options) or ordered rubric scores, each answer with a confidence score from 0 to 1.
- The model scores options in a single forward pass without token-by-token decoding, at 150 to 250 ms end-to-end; it costs $0.10 per million input tokens with no output tokens billed, and the shared input is billed once per request.
- Google says it is nearly 5x cheaper across its shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API; Gemini Notebook uses it as a real-time router, serving everyday queries with up to 40% lower latency.
- Integrations are rolling out across OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI and others, with support coming soon to Gemini in Google Cloud.
Builder's takeRead with the 11-11 item on Hugging Face's common interface for decision models: picking from options is being split out of generative calls. I would move two kinds of calls first, grading interview answers against a rubric in AI Interview and pre-publish policy checks in PandaClaws, set a confidence threshold, and send only low-confidence cases to a large model or a person, then compare accuracy and cost per call before switching.
// Background · from #Google
Full timeline →- Nov 12 DeepMind releases AlphaGenome 2: it predicts variant effects per cell type and finds nearly twice as many causal variants as its predecessor (30% vs 16%)
- Nov 11 Gemini 4 Carbon opens to all developers at Argon's introductory price of $2 input and $10 output per million tokens
- Nov 11 DeepMind introduces AlphaProof Code: agents generate over six million lines of Lean to formally verify Signal's protocol implementation in four weeks