Gemini Decision 1 API

Q: What is the Gemini Decision 1 model ID?

Use google/gemini-decision-1 as the model parameter. Requests go to https://api.aimlapi.com/v1/decisions with your AI/ML API key.

Try this model

Route requests, check policies and score candidates with calibrated yes/no, choice and rubric answers

Modalities: TextText
Input price: $0.1058per 1M tokens
Context window: 256K tokens
Released: Nov 11, 2026

Gemini Decision 1 overview

Decision example

The blue mug I ordered on Monday arrived cracked on Wednesday.

Question	Result
Damaged item	P(yes): 0.9873
Team	returns (confidence 0.9979)
Urgency	0.2270 / 2 (confidence 0.7866)

Actual model response from Nov 12, 2026.

View request and response

Request

{
  "model": "google/gemini-decision-1",
  "state": "The blue mug I ordered on Monday arrived cracked on Wednesday.",
  "questions": {
    "damaged_item": {
      "type": "noul",
      "instructions": "Does the customer report an item that arrived damaged?"
    },
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this request?",
      "criteria": {
        "returns": "Damaged products, replacements and returns",
        "billing": "Payments, invoices and charges",
        "technical": "App errors and integrations"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "Rate how urgently the request needs attention.",
      "criteria": [
        "Routine follow-up",
        "Customer is blocked",
        "Immediate safety risk"
      ]
    }
  }
}

Response

{
  "model": "google/gemini-decision-1-20261111",
  "answers": {
    "damaged_item": {
      "type": "noul",
      "noul": 0.9872533176624986,
      "confidence": 0.9872533176624986
    },
    "urgency": {
      "type": "score",
      "score": 0.22698175101837453,
      "legend": {
        "0": "Routine follow-up",
        "1": "Customer is blocked",
        "2": "Immediate safety risk"
      },
      "probabilities": {
        "0": 0.7866341621034817,
        "1": 0.19974992477466214,
        "2": 0.013615913121856204
      },
      "confidence": 0.7866341621034817
    },
    "team": {
      "type": "choice",
      "choice": "returns",
      "probabilities": {
        "returns": 0.9978734172735529,
        "billing": 0.0007264764239649078,
        "technical": 0.0014001063024821076
      },
      "confidence": 0.9978734172735529
    }
  },
  "usage": {
    "input_tokens": 232,
    "output_tokens": 0
  }
}

Gemini Decision 1 by Google

Gemini Decision 1 returns typed probabilities, choices and rubric scores. Up to 1,000 questions can share the same text input on AI/ML API.

Gemini Decision 1 specs

Model ID: google/gemini-decision-1
Developer: Google
Context window: 262,144 tokens
Input: Text
Output: Text
Endpoint: POST https://api.aimlapi.com/v1/decisions

Ask several questions about one input

Gemini Decision 1 accepts up to 1,000 questions about the same input. The AI/ML API endpoint accepts text as a string, a JSON object or an array of texts. The context window holds 262,144 tokens.

Group related checks into one request when they all need the same document.

Choose the result your application needs

A yes-or-no question returns a probability from 0 to 1. A choice question selects one of 2 to 255 options and returns the selected key, confidence and the probability of each option. A rubric score uses 2 to 10 ordered levels and returns a probability-weighted level index, which can be fractional.

Use a choice for a destination team or label. Use a rubric score when the possible answers have an order.

Set thresholds on labelled examples

Google describes Gemini Decision 1 as a model for request routing, policy checks, rubric scoring and tool selection. Test the returned probabilities and choices against labelled inputs from your own workflow before setting automatic routing thresholds.

Use cases

Route incoming support tickets to the right queue with a single-select question over the ticket text.

Check a draft message against a content policy with a set of yes-or-no questions in one request.

Score candidate answers or applications against a rubric with ordered levels and read the expected score.

Choose which tool an agent should call next by asking a single-select question over the user request.

Gemini Decision 1 API pricing

Gemini Decision 1 pricing in US dollars
Usage	Price	Unit
Input	$0.1058	1M tokens

Prices from the AI/ML API price list, checked on Nov 12, 2026.

How to use the Gemini Decision 1 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/decisions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemini-decision-1",
  "state": "The blue mug I ordered on Monday arrived cracked on Wednesday.",
  "questions": {
    "damaged_item": {
      "type": "noul",
      "instructions": "Does the customer report an item that arrived damaged?"
    },
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this request?",
      "criteria": {
        "returns": "Damaged products, replacements and returns",
        "billing": "Payments, invoices and charges",
        "technical": "App errors and integrations"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "Rate how urgently the request needs attention.",
      "criteria": [
        "Routine follow-up",
        "Customer is blocked",
        "Immediate safety risk"
      ]
    }
  }
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemini-decision-1",
    "state": "The blue mug I ordered on Monday arrived cracked on Wednesday.",
    "questions": {
        "damaged_item": {
            "type": "noul",
            "instructions": "Does the customer report an item that arrived damaged?"
        },
        "team": {
            "type": "choice",
            "instructions": "Which team should handle this request?",
            "criteria": {
                "returns": "Damaged products, replacements and returns",
                "billing": "Payments, invoices and charges",
                "technical": "App errors and integrations"
            }
        },
        "urgency": {
            "type": "score",
            "instructions": "Rate how urgently the request needs attention.",
            "criteria": [
                "Routine follow-up",
                "Customer is blocked",
                "Immediate safety risk"
            ]
        }
    }
}

response = requests.post("https://api.aimlapi.com/v1/decisions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/decisions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-decision-1",
    "state": "The blue mug I ordered on Monday arrived cracked on Wednesday.",
    "questions": {
      "damaged_item": {
        "type": "noul",
        "instructions": "Does the customer report an item that arrived damaged?"
      },
      "team": {
        "type": "choice",
        "instructions": "Which team should handle this request?",
        "criteria": {
          "returns": "Damaged products, replacements and returns",
          "billing": "Payments, invoices and charges",
          "technical": "App errors and integrations"
        }
      },
      "urgency": {
        "type": "score",
        "instructions": "Rate how urgently the request needs attention.",
        "criteria": [
          "Routine follow-up",
          "Customer is blocked",
          "Immediate safety risk"
        ]
      }
    }
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Gemini Decision 1 FAQ

How much does Gemini Decision 1 cost?

Gemini Decision 1 is billed at $0.1058 / 1M tokens for input. There are no output-token charges.

What input can I send?

This AI/ML API endpoint accepts text as a string, a JSON object or an array of texts.

What does a yes-or-no question return?

It returns the probability of yes, from 0 to 1. Use that probability when setting a decision threshold.

How many choices can one question have?

A choice question accepts 2 to 255 options and returns the selected key, confidence and a probability for each option.

How does a rubric score work?

Define 2 to 10 ordered levels. The result is a probability-weighted level index, which can be fractional, with confidence and per-level probabilities.

What is the Gemini Decision 1 model ID?

Use google/gemini-decision-1 as the model parameter. Requests go to https://api.aimlapi.com/v1/decisions with your AI/ML API key.

Start building with Gemini Decision 1

Get API key

Gemini Decision 1 API

google/gemini-decision-1

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/decisions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemini-decision-1",
  "state": "The blue mug I ordered on Monday arrived cracked on Wednesday.",
  "questions": {
    "damaged_item": {
      "type": "noul",
      "instructions": "Does the customer report an item that arrived damaged?"
    },
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this request?",
      "criteria": {
        "returns": "Damaged products, replacements and returns",
        "billing": "Payments, invoices and charges",
        "technical": "App errors and integrations"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "Rate how urgently the request needs attention.",
      "criteria": [
        "Routine follow-up",
        "Customer is blocked",
        "Immediate safety risk"
      ]
    }
  }
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemini-decision-1",
    "state": "The blue mug I ordered on Monday arrived cracked on Wednesday.",
    "questions": {
        "damaged_item": {
            "type": "noul",
            "instructions": "Does the customer report an item that arrived damaged?"
        },
        "team": {
            "type": "choice",
            "instructions": "Which team should handle this request?",
            "criteria": {
                "returns": "Damaged products, replacements and returns",
                "billing": "Payments, invoices and charges",
                "technical": "App errors and integrations"
            }
        },
        "urgency": {
            "type": "score",
            "instructions": "Rate how urgently the request needs attention.",
            "criteria": [
                "Routine follow-up",
                "Customer is blocked",
                "Immediate safety risk"
            ]
        }
    }
}

response = requests.post("https://api.aimlapi.com/v1/decisions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/decisions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-decision-1",
    "state": "The blue mug I ordered on Monday arrived cracked on Wednesday.",
    "questions": {
      "damaged_item": {
        "type": "noul",
        "instructions": "Does the customer report an item that arrived damaged?"
      },
      "team": {
        "type": "choice",
        "instructions": "Which team should handle this request?",
        "criteria": {
          "returns": "Damaged products, replacements and returns",
          "billing": "Payments, invoices and charges",
          "technical": "App errors and integrations"
        }
      },
      "urgency": {
        "type": "score",
        "instructions": "Rate how urgently the request needs attention.",
        "criteria": [
          "Routine follow-up",
          "Customer is blocked",
          "Immediate safety risk"
        ]
      }
    }
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Gemini Decision 1 API

Gemini Decision 1 overview

Decision example

Request

Response

Gemini Decision 1 by Google

Gemini Decision 1 specs

Ask several questions about one input

Choose the result your application needs

Set thresholds on labelled examples

Use cases

Gemini Decision 1 API pricing

How to use the Gemini Decision 1 API

Build with your agent

1Get your API key

2Make your first request

Gemini Decision 1 FAQ

Start building with Gemini Decision 1

Gemini Decision 1 API

Build with your agent

1Get your API key

2Make your first request

Gemini Decision 1 API

Gemini Decision 1 overview

Decision example

Request

Response

Gemini Decision 1 by Google

Gemini Decision 1 specs

Ask several questions about one input

Choose the result your application needs

Set thresholds on labelled examples

Use cases

Gemini Decision 1 API pricing

How to use the Gemini Decision 1 API

Build with your agent

1Get your API key

2Make your first request

Models similar to Gemini Decision 1

Jev 1.14

Jev 1.13

d1

Gemini Decision 1 FAQ

Start building with Gemini Decision 1