Today ainotis Join

My notis

ModelsPublished Top storyAll news from that day

Ongoing case: Typed decision models and APIs New model · 8 stories

Google releases Gemini Decisions API, which returns probabilities for up to 1,000 questions

The gemini-decision-1 model produces no text output, so Google charges $0.10 per million input tokens only; Google says it has the lowest calibration error in its own comparison.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

Share

Check our sources · 11 facts from 4 sources
Header artwork for the Gemini Decisions API launch post, Google's own illustration of the releaseImage: Google
source · The company's own image of its product, used to report on it

Key points

  1. A request takes shared input up to 262,144 tokens and up to 1,000 independent questions; a yes/no answer returns a probability from 0.01 to 0.99.
  2. Google says median latency is 150-250 ms up to 16K tokens, and it is nearly 5x cheaper than Gemini 3.5 Flash-Lite with the Interactions API across the shared benchmark suite.
  3. The paid tier costs $0.10 per million input tokens and $0 for output; context caching, the Batch API, and Flex or Priority inference are not supported.

What happened

Google released the Gemini Decisions API on 11 November, an endpoint that answers yes/no, multiple-choice and rubric questions about one shared input and returns probabilities instead of text. It runs on a new model, gemini-decision-1, in the Gemini API's v1beta version. Google DeepMind's Min Choi and Felix Yu announced it in a blog post.

Google says it is meant for bounded choices such as tool selection, policy checks, model routing and context grading. One request can carry text, images, audio, video or PDFs up to 262,144 tokens and up to 1,000 independent questions. A yes/no answer comes back with a probability and a confidence score, a choice question takes 2 to 255 options, and a rubric question takes 2 to 255 ordered levels.

Google says the model leads on benchmarks spanning agent routing, reasoning, ranking and multimodal understanding, with the lowest calibration error. The post's text does not name those benchmarks, and the comparison is Google's own.

It also says the model scores options without token-by-token decoding, a median of 150 to 250 milliseconds for contexts up to 16K tokens, and that it is nearly 5 times cheaper across the shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API.

Google says one of its own products, Gemini Notebook, uses it as a router. Google says Gemini Notebook uses the API to send each query to the right model tier and thinking level, which it says serves everyday queries with up to 40% lower latency.

The paid tier costs $0.10 per million input tokens, with no charge for output because the model generates none. The shared input is billed once per request however many questions are asked, and each question adds only its own instructions and criteria. There is a free tier in Google AI Studio for prototyping.

The docs list limits: no context caching, no Batch API, and no Flex or Priority inference. They also tell developers to treat input as untrusted, because user-supplied text can argue for its own classification. Google says integrations are rolling out across OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode, with support for Gemini in Google Cloud coming soon.

This note continues the case on typed decision models and APIs.

What it means for you

Our view

The API is built for bounded choices such as routing, policy checks and context grading, so it suits a different job from a general model. Google's latency and cost comparisons are its own, and the post's text does not name the benchmarks behind them.

The docs also warn that user-supplied text can argue for its own classification, which matters when an answer gates an action. Compare the listed limits with your own request volume before you build a routing layer on it.

It adds no new facts.

Share this story

Your reaction

We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.

Check our sources

Every sentence above is checked against these 4 sources.

1 Gemini Decisions API: Fast, calibrated multimodal decisions (11 Nov 2026)Google · 11 Nov 2026 · 7 facts Open the source archived copy

  1. Google's blog post of 11 November 2026, by Min Choi (Product Manager) and Felix Yu (Principal Scientist) of Google DeepMind, says: "Today, we're introducing the Gemini Decisions API, a new endpoint for fast, closed-set decisions powered by our new Gemini Decision 1 model (gemini-decision-1), available through the Gemini API in Google AI Studio."

    Nov 11, 2026 ... Min Choi Product Manager, Google DeepMind Felix Yu Principal Scientist, Google DeepMind ... Today, we’re introducing the Gemini Decisions API, a new endpoint for fast, closed-set decisions powered by our new Gemini Decision 1 model (gemini-decision-1), available through the Gemini API in Google AI Studio .
    cite

  2. Google says the Decisions API gives "purpose-built primitives for bounded choices like tool selection, policy checks, model routing, and context grading."

    The Decisions API gives you purpose-built primitives for bounded choices like tool selection, policy checks, model routing, and context grading.
    cite

  3. Google says: "On benchmarks spanning agent routing, reasoning, ranking, and multimodal understanding, Gemini Decision 1 leads across the suite, with the lowest calibration error." The post text does not name the benchmarks; the comparison is Google's own.

    On benchmarks spanning agent routing, reasoning, ranking, and multimodal understanding, Gemini Decision 1 leads across the suite, with the lowest calibration error.
    cite

  4. Google says Gemini Decision 1 scores options without token-by-token decoding, keeping median latency at "150-250 ms end-to-end" across multimodal inputs and contexts up to 16K tokens, and that "With zero output tokens billed, Gemini Decision 1 with the Decisions API is nearly 5x cheaper across the shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API."

    Toned down to what the source says
    Gemini Decision 1 scores options without token-by-token decoding, keeping median latency 50-100 ms of model compute (150-250 ms end-to-end), across multimodal inputs and contexts up to 16K tokens, remaining nearly flat from 1 to 100 questions per request. With zero output tokens billed, Gemini Decision 1 with the Decisions API is nearly 5x cheaper across the shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API.
    cite

  5. Google says Gemini Notebook "uses the Decisions API as a real-time router to instantly direct incoming queries to the optimal model tier and thinking level for each request", serving "everyday queries with up to 40% lower latency while reserving deep reasoning models for complex tasks." This is Google's account of its own product.

    Gemini Notebook uses the Decisions API as a real-time router to instantly direct incoming queries to the optimal model tier and thinking level for each request. The Decisions API classifies intent in milliseconds to serve everyday queries with up to 40% lower latency while reserving deep reasoning models for complex tasks.
    cite

  6. Google says Gemini Decision 1 "is priced at $0.10 per 1M input tokens and $0 for output tokens, with an API no-cost tier you can use in Google AI Studio for prototyping."

    Gemini Decision 1 is priced at $0.10 per 1M input tokens and $0 for output tokens, with an API no-cost tier you can use in Google AI Studio for prototyping.
    cite

  7. Google says ecosystem integrations "are rolling out across OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit, and OpenCode alongside the google-genai SDKs, with support coming soon to Gemini in Google Cloud."

    Ecosystem integrations are rolling out across OpenRouter , LangChain , Vercel , LiteLLM , Pydantic AI , Pipecat , LiveKit , and OpenCode alongside the google-genai SDKs, with support coming soon to Gemini in Google Cloud.
    cite
2 Decisions API guide, Gemini API docsGoogle · 2 facts Open the source archived copy

  1. The Decisions API guide says it "evaluates typed questions against your data using Gemini Decision 1 and returns calibrated probabilities. It generates zero text tokens, so output token usage is always 0." Its Limitations section says it is available on the Gemini Developer API (v1beta) with Gemini Decision 1 only.

    The Decisions API evaluates typed questions against your data using [Gemini Decision 1](/docs/models/gemini-decision-1) and returns calibrated probabilities. It generates zero text tokens, so output token usage is always 0. ... ## Limitations {% id="limitations" %} * Available on the Gemini Developer API (v1beta) with [Gemini Decision 1](/docs/models/gemini-decision-1) only.
    cite

  2. The Decisions API guide's Limitations section says it doesn't support context caching, the Batch API, or Flex or Priority inference. Its best practices say: "Treat input as untrusted. User-supplied text can argue for its own classification."

    The Decisions API doesn't support context caching, [Batch API](/docs/batch-api), or Flex or Priority inference. ... Treat input as untrusted. User-supplied text can argue for its own classification.
    cite
3 Gemini Decision model page, Gemini API docsGoogle · 1 fact Open the source archived copy

  1. The Gemini Decision model page says a single request can evaluate up to 1,000 independent questions over shared input up to 262,144 tokens, across text, images, video, audio and PDFs. Yes/no returns a calibrated probability from 0.01 to 0.99 and a confidence score; single-select evaluates 2 to 255 options; rubric rating evaluates 2 to 255 ordered levels.

    cite
4 Gemini Developer API pricingGoogle · 7 Oct 2026 · 1 fact Open the source archived copy

  1. The Gemini API pricing page lists Gemini Decision (gemini-decision-1) at $0.10 per 1M input tokens on the paid tier, free of charge on the free tier, output not applicable (0 output tokens), and context caching not available. It says each request bills shared input tokens once regardless of question count, and that the Batch API isn't supported.

    cite

Topics

The morning email

On the mornings we publish: the three top stories and up to four short ones. Free.

We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep