> ## AI Agent Context
> Get the complete documentation index at: https://aistudio.google.com/llms.txt
> Use this file to discover all available pages.
> For the full documentation in a single file, fetch: https://aistudio.google.com/llms-full.txt

# Gemini Decision

Gemini Decision is a specialized multimodal model built for the
[Decisions API](/docs/decisions-api). It evaluates typed questions over text,
images, video, audio, and PDFs in a single prefill pass and returns calibrated
outcome probabilities with zero output tokens.

Use Gemini Decision for request routing, policy checks across many rules at
once, candidate scoring against a rubric, tool selection, and low-latency
classification over live media streams. A single request can evaluate up to
1,000 independent questions over shared input up to 262,144 tokens:

*   **Yes/no:** Returns a calibrated probability from 0.01 to 0.99 and a
  confidence score.
*   **Single-select:** Evaluates 2 to 255 options and returns the top option,
  per-option probabilities, and confidence.
*   **Rubric rating:** Evaluates 2 to 255 ordered rubric levels and returns the
  probability-weighted expected score, per-level probabilities, and
  confidence.

{% button href="/docs/decisions-api" variant="primary" %}View documentation{% /button %}

## Quickstart  {% id="quickstart" %}

Evaluate a yes/no question and a routing choice over the same customer message
in one call:

{% tabs %}
  {% tab filename="decisions.py" label="Python" %}
  ```python
  from google import genai
  
  client = genai.Client(http_options={"api_version": "v1beta"})
  
  result = client.decisions.create(
      model="gemini-decision-1",
      input="The blue mug I ordered on Monday arrived cracked on Wednesday.",
      questions={
          "is_damaged": {
              "type": "noul",
              "instructions": "Did the item arrive damaged?",
          },
          "queue": {
              "type": "choice",
              "instructions": "Which support queue should handle this message?",
              "criteria": {
                  "billing": "Payment, invoice, or refund questions.",
                  "replacements": "Damaged, missing, or wrong items.",
                  "general": "Product questions and account updates.",
              },
          },
      },
  )
  
  damaged = result.answers["is_damaged"]
  queue = result.answers["queue"]
  print(f"P(damaged)={damaged.noul:.2f} queue={queue.choice}")
  ```

  {% /tab %}

  {% tab filename="decisions.mjs" label="JavaScript" %}
  ```javascript
  import { GoogleGenAI } from "@google/genai";
  
  const ai = new GoogleGenAI({ apiVersion: "v1beta" });
  
  const result = await ai.decisions.create({
    model: "gemini-decision-1",
    input: "The blue mug I ordered on Monday arrived cracked on Wednesday.",
    questions: {
      is_damaged: {
        type: "noul",
        instructions: "Did the item arrive damaged?",
      },
      queue: {
        type: "choice",
        instructions: "Which support queue should handle this message?",
        criteria: {
          billing: "Payment, invoice, or refund questions.",
          replacements: "Damaged, missing, or wrong items.",
          general: "Product questions and account updates.",
        },
      },
    },
  });
  
  const damaged = result.answers?.is_damaged;
  const queue = result.answers?.queue;
  if (damaged?.type === "noul" && queue?.type === "choice") {
    console.log(`P(damaged)=${damaged.noul} queue=${queue.choice}`);
  }
  ```

  {% /tab %}

  {% tab filename="decisions.sh" label="REST" %}
  ```bash
  curl -X POST "https://generativelanguage.googleapis.com/v1beta/decisions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gemini-decision-1",
      "input": "The blue mug I ordered on Monday arrived cracked on Wednesday.",
      "questions": {
        "is_damaged": {
          "type": "noul",
          "instructions": "Did the item arrive damaged?"
        },
        "queue": {
          "type": "choice",
          "instructions": "Which support queue should handle this message?",
          "criteria": {
            "billing": "Payment, invoice, or refund questions.",
            "replacements": "Damaged, missing, or wrong items.",
            "general": "Product questions and account updates."
          }
        }
      }
    }'
  ```

  {% /tab %}

{% /tabs %}

## Documentation  {% id="documentation" %}

Visit the [Decisions API](/docs/decisions-api) guide for request schemas,
criteria design, multimodal inputs, and calibration details. See
[Pricing](/docs/pricing#gemini-decision) and
[Rate limits](/docs/rate-limits#gemini-decision) for billing and quota tiers.

## Sample apps  {% id="sample-apps" %}

Explore interactive sample apps in Google AI Studio built with Gemini Decision:

*   [Decisions Playground](https://aistudio.google.com/apps/f6cbef57-8bad-443a-813f-4d4c8f9750af?fullscreenApplet=true):
  Test yes/no, choice, and score questions interactively on custom text and
  media inputs.
*   [Doorstep Parcels](https://aistudio.google.com/apps/bdca3fee-8d0a-4663-b30e-73828a55c1e8?fullscreenApplet=true):
  Classify delivery photos for package condition and placement using
  calibrated probabilities.
*   [Find the Zookeeper](https://aistudio.google.com/apps/b86d2f3b-c1d4-4d44-9198-5303a0cb65c1?fullscreenApplet=true):
  Evaluate visual attributes across scene candidates in a single pass.

## gemini-decision-1  {% id="gemini-decision-1" %}

{% table variant="model" %}
  * Property
  * Description

  ---

  *     {% section class="model-property" %}
  {% icon name="id_card" /%}Model code

    {% /section %}

  * `gemini-decision-1`

  ---

  *     {% section class="model-property" %}
  {% icon name="save" /%}Supported data types

    {% /section %}

  *     **Inputs** Text, Image, Video, Audio, and PDF

    **Output** Calibrated probabilities (yes/no, choice, and score, with 0 output tokens)


  ---

  *     {% section class="model-property" %}
  {% icon name="token_auto" /%}Token limits{% sup %}[[*]](/docs/tokens){% /sup %}

    {% /section %}

  *     **Input token limit** 262,144

    **Output token limit** 0 (up to 1,000 questions per request)


  ---

  *     {% section class="model-property" %}
  {% icon name="handyman" /%}Capabilities

    {% /section %}

  *     {% section class="three-column-grid" %}
  {% section %}
  [**Calibrated decisions**](/docs/decisions-api)

  {% badge type="supported" /%}

  {% /section %}

  {% section %}
  **Audio generation**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Batch API**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Caching**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Code execution**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Computer use**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **File search**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Flex inference**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Function calling**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Grounding with Google Maps**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Image generation**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Live API**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Priority inference**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Search grounding**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Structured outputs**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Text generation**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **Thinking**

  {% badge type="not-supported" /%}

  {% /section %}

  {% section %}
  **URL context**

  {% badge type="not-supported" /%}

  {% /section %}

    {% /section %}


  ---

  *     {% section class="model-property" %}
  {% icon name="123" /%}Versions

    {% /section %}

  *     Read the [model version patterns](/docs/models#model-versions) for more details.

    *   `gemini-decision-1`


  ---

  *     {% section class="model-property" %}
  {% icon name="calendar_month" /%}Latest update

    {% /section %}

  * November 2026

  ---

  *     {% section class="model-property" %}
  {% icon name="speed" /%}Rate limits

    {% /section %}

  * [Rate limits](/docs/rate-limits#gemini-decision)

  ---

  *     {% section class="model-property" %}
  {% icon name="paid" /%}Pricing

    {% /section %}

  * [Pricing](/docs/pricing#gemini-decision)
{% /table %}