# Gemini Decision 1

> Gemini Decision 1 is Google's decision model for the Gemini Decisions API. It scores yes/no, choice, and rubric questions on one text, image, audio, video, or PDF input in a single pass, with a 262,144-token context window.

**ID**: `google/gemini-decision-1`  
**Creator**: Google  
**Category**: text  
**Context**: 262K tokens  
**Pricing**: $0.10 / $0 per 1M · billed by your provider (BYOK)  
**Released**: 2026-11-11  
**Web page**: https://anyrouter.dev/model/google/gemini-decision-1

**Input modalities**: text, image, audio, video, file  
**Output modalities**: text  

**Capabilities**: systemone

**Supported parameters**: state, model, questions

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/decisions`

```bash
curl https://anyrouter.dev/api/v1/decisions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "state": "Help! My payouts have been failing for 3 days.",
  "model": "google/gemini-decision-1",
  "questions": {
    "is_urgent": {
      "type": "noul",
      "instructions": "Does this convey urgency?"
    }
  }
}'
```

Decisions is not chat: send `state` and typed `questions` (noul / choice / score). Requires a BYOK key for TypeSafe, LLM Gateway, Vercel AI Gateway, AIHubMix, AutoJev, or Fastino.

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| openrouter-byok | $0.10/M (list) | $0 (list) |
| vercel-byok | $0.10/M (list) | $0 (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Model card

- Native context: 262144 tokens [1]

### Strengths [1]

- Scores up to a thousand yes/no, choice, and rubric questions on one multimodal input in a single forward pass
- Returns a calibrated probability for every answer, with 150-250 ms end-to-end latency
- Nearly 5x cheaper than Gemini 3.5 Flash-Lite with the Interactions API across the vendor's shared benchmark suite

### Known limits [1]

- Answers fixed questions; it does not generate chat text

### Use cases [1]

- Tool selection and agent routing
- Policy checks and context grading
- Ranking and scoring candidate outputs

### API notes [1,2]

- System One envelope with a state plus named yes/no, choice, or score questions
- Text, image, audio, video, and PDF input in one request
- Up to a thousand independent questions per request

### Links

- announcement: https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/
- docs: https://aistudio.google.com/docs/decisions-api
- pricing: https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/
- social: [object Object],[object Object],[object Object]

### Sources

1. [Gemini Decisions API: Fast, calibrated multimodal decisions](https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/) (accessed 2026-11-11)
2. [Gemini Decisions API documentation](https://aistudio.google.com/docs/decisions-api) (accessed 2026-11-11)

## Source

- Upstream docs: https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/