{"schema":"sanctity-signal/0.2","record_type":"signal","id":"google-gemini-decisions-api-e088","domain":"labs","drop_id":"signal-e088","occurred_at":"2026-11-11","how_to_use":"This is a structured record of one real-world action and its competing interpretations, from Sanctity Signal. To build content from it (a reel script, a blog, a thread): open on the hook, ground the viewer with plain and observed, walk the dated trail, present the interpretations as live tension between named readings, and close on the before/after shift and what_to_watch. Hard rules: items under established are fact; items under unknown are never presented as fact; the evidence status (verified or reported) is stated, not dropped; sources are cited.","actor":"Google","action_type":"release of the Gemini Decisions API and the gemini-decision-1 model, a scoring endpoint billed only on input tokens, in the Gemini API and AI Studio","observed":"Google published \"Gemini Decisions API: Fast, calibrated multimodal decisions\" on blog.google on November 11, 2026 at 18:00 Universal Time, written by Min Choi, a product manager at Google DeepMind, and Felix Yu, a principal scientist there. We read it there. The endpoint scores a fixed set of candidate answers against one shared input instead of generating text: \"Gemini Decision 1 scores your candidate options in a single forward pass.\" The model is named gemini-decision-1 and is reachable through the Gemini API and Google AI Studio, with Python, JavaScript and REST guides and the google-genai software kit at version 3.2 or later. Three question types are offered: a yes-or-no form returning the probability a condition holds; a multiple-choice form taking 2 to 255 options and returning normalised probabilities; and an ordered rubric form starting at 0 that returns a weighted score with per-level probabilities. Every answer carries a confidence score from 0 to 1, which Google frames as a route to a fallback or a human reviewer. Inputs may be text, images, audio, video and PDFs, up to 256,000 tokens covering the shared input and all questions together, and one request may carry up to 1,000 questions. Google reports 150 to 250 milliseconds end to end, of which 50 to 100 milliseconds is model compute, and says latency stays nearly flat from 1 to 100 questions for contexts up to 16,000 tokens. Pricing is $0.10 per 1 million input tokens with no charge for output tokens, no variable thinking-token charge, and no separate audio transcription or character recognition charge; the shared input is billed once per request, and each question adds only its own instruction tokens. A free tier is offered in AI Studio. Google says the model \"leads across the suite, with the lowest calibration error\" on agent routing, reasoning, ranking and multimodal benchmarks, and that the product is nearly 5 times cheaper across that suite than Gemini 3.5 Flash-Lite on the Interactions API. Named internal uses: model routing in Gemini Notebook, reported at up to 40% lower latency for everyday queries; wireframing in Stitch; emoji selection from more than 200 options in CC from Google Labs; and a safety layer in Google Search that screens tool calls for adversarial behaviour. Not published: any accuracy or calibration figure, the benchmark names, or the model's size. Listed as unavailable: context caching, batch inference, priority inference, conversation history and tool-call blocks.","corrections":[],"evidence":{"status":"verified","note":null,"sources":[{"role":"primary","label":"Google: Gemini Decisions API, fast calibrated multimodal decisions, blog.google, Nov 11, 2026, 18:00 Universal Time","url":"https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/"},{"role":"corrob","label":"Unite.AI: Google launches Gemini Decisions API for multimodal AI workflows, Nov 11, 2026","url":"https://www.unite.ai/google-launches-gemini-decisions-api-for-multimodal-ai-workflows/"},{"role":"corrob","label":"Cryptobriefing: Google launches Gemini Decisions API for fast multimodal choices, Nov 11, 2026","url":"https://cryptobriefing.com/google-gemini-decisions-api-launch/"}]},"strength":{"cost":"Medium","commitment":"Medium","reversibility":"Easy","persistence":"Year","rationale":"Cost is medium. Training a separate decision model and standing up a new endpoint is real engineering, but it is one API among many and no capital is committed. Commitment is medium: Google has published prices and documentation, which are hard to withdraw quietly, yet the model sits in the developer API alone, with Gemini in Google Cloud listed as coming later. Reversibility is easy. Google has retired preview endpoints before and nothing here is contractual. Persistence is a year rather than structural, because the pricing shape, zero output cost, is the part competitors can copy within weeks, and probably will."},"shift":{"prior":"Agents decide by generating text and then parsing it.","action":"Google published \"Gemini Decisions API: Fast, calibrated multimodal decisions\" on blog.google on November 11, 2026 at 18:00 Universal Time, written by Min Choi, a product manager at Google DeepMind, and Felix Yu, a principal scientist there. We read it there. The endpoint scores a fixed set of candidate answers against one shared input instead of generating text: \"Gemini Decision 1 scores your candidate options in a single forward pass.\" The model is named gemini-decision-1 and is reachable through the Gemini API and Google AI Studio, with Python, JavaScript and REST guides and the google-genai software kit at version 3.2 or later. Three question types are offered: a yes-or-no form returning the probability a condition holds; a multiple-choice form taking 2 to 255 options and returning normalised probabilities; and an ordered rubric form starting at 0 that returns a weighted score with per-level probabilities. Every answer carries a confidence score from 0 to 1, which Google frames as a route to a fallback or a human reviewer. Inputs may be text, images, audio, video and PDFs, up to 256,000 tokens covering the shared input and all questions together, and one request may carry up to 1,000 questions. Google reports 150 to 250 milliseconds end to end, of which 50 to 100 milliseconds is model compute, and says latency stays nearly flat from 1 to 100 questions for contexts up to 16,000 tokens. Pricing is $0.10 per 1 million input tokens with no charge for output tokens, no variable thinking-token charge, and no separate audio transcription or character recognition charge; the shared input is billed once per request, and each question adds only its own instruction tokens. A free tier is offered in AI Studio. Google says the model \"leads across the suite, with the lowest calibration error\" on agent routing, reasoning, ranking and multimodal benchmarks, and that the product is nearly 5 times cheaper across that suite than Gemini 3.5 Flash-Lite on the Interactions API. Named internal uses: model routing in Gemini Notebook, reported at up to 40% lower latency for everyday queries; wireframing in Stitch; emoji selection from more than 200 options in CC from Google Labs; and a safety layer in Google Search that screens tool calls for adversarial behaviour. Not published: any accuracy or calibration figure, the benchmark names, or the model's size. Listed as unavailable: context caching, batch inference, priority inference, conversation history and tool-call blocks.","update":"Deciding is a separate priced product, billed only on input."},"inference":{"established":["Gemini Decision 1 is live in the Gemini API and AI Studio.","One request takes up to 1,000 questions over 256,000 tokens.","Pricing is $0.10 per million input tokens, with output free."],"unknown":["That it is more accurate. No accuracy numbers were published.","That the 40% latency gain holds outside Google's own notebook.","That confidence scores are reliable. Calibration error is claimed, not shown."]},"narrative":{"hook":"Google shipped a model that only decides, priced at $0.10 per million input tokens.","plain":"On November 11 Google launched the Gemini Decisions API and Gemini Decision 1. Caveat: Google published no accuracy figures, only the claim that it leads its own benchmarks.","story":["Every agent makes hundreds of small choices: which tool, is this allowed, which model. Google has made that layer a separate product, charges only for input, and reports 150 to 250 milliseconds end to end. Cheap, fast judgment makes more agent steps affordable, and more steps means less human review."],"trail":[{"d":"OCT 8","t":"Google Cloud gives its enterprise agents their own Workspace accounts and directory entries, making an agent an addressable member of a company. Edition 047."},{"d":"NOV 5","t":"OpenAI releases GPT-6 Cyber to defenders first. Capability is increasingly shipped as a narrow product rather than one general model. Edition 076."},{"d":"NOV 9","t":"Google launches 2 AI chips, one built to protect model weights while in use, pushing more of the stack into purpose-built parts. Edition 083."},{"d":"NOV 10","t":"OpenAI puts business agents into ChatGPT and Mercor prices the human work behind evaluation at $20 billion. The judging layer becomes a market. Editions 086 and 087."},{"d":"NOV 11","t":"Google ships the Gemini Decisions API and gemini-decision-1 at $0.10 per 1 million input tokens, output free, up to 1,000 questions per request."},{"d":"Reacts","r":true,"t":"Every agent framework that pays a general model to make small choices; OpenAI and Anthropic, whose cheapest models are now the comparison; OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode, named as integrations; evaluation vendors that sell judging; and the teams who set how often a human sees an agent's decision."}],"glossary":[{"term":"Inference","def":"The step where a trained model produces an answer. It is billed per token and is the running cost of any AI product."},{"term":"Calibration error","def":"The gap between a model's stated confidence and how often it is right. Low error means a 70% score really means about 70%."},{"term":"Model routing","def":"Sending each request to the cheapest model that can handle it. The router must itself be fast and cheap, or it eats the saving."},{"term":"Forward pass","def":"One run of the model over its input. Scoring options in a single pass avoids generating text and then parsing it."}]},"judgment":{"prompt":"Which explanation do you believe?","interpretations":[{"id":"a","label":"Judgment becomes its own product","text":"A separate calibrated model for choices, not a chat model doing them.","abstain":false},{"id":"b","label":"Defending the cheap tier","text":"Rivals undercut Google at the bottom. This answers on price.","abstain":false},{"id":"c","label":"Priced to be bought in volume","text":"Input-only billing and shared input fit agents asking hundreds of questions.","abstain":false},{"id":"d","label":"Normal API expansion","text":"Google ships many endpoints. This one is small and narrow.","abstain":false},{"id":"e","label":"Too early to call.","text":"The evidence cannot yet separate these.","abstain":true}],"distribution":{"status":"held back until you have made your call","calls":null}},"story_thread":null,"what_to_watch":[{"linked_interpretation":"c","direction":"strengthens","observable_event":"OpenAI or Anthropic ships a decision or classification endpoint that bills input only, or Google reports paid volume for the Decisions API, by June 30, 2027.","window_end":"2027-06-30","state":"unresolved"},{"linked_interpretation":"a","direction":"weakens","observable_event":"Google retires gemini-decision-1 or folds it into a general model, or publishes no accuracy figures and names no customer outside Google, by December 31, 2027.","window_end":"2027-12-31","state":"unresolved"},{"linked_interpretation":"a","direction":"strengthens","observable_event":"An independent evaluation shows gemini-decision-1 beating a general model of similar cost on routing or policy checks, by September 30, 2027.","window_end":"2027-09-30","state":"unresolved"}]}