# Gemini Decision 1 pricing and access by Google DeepMind

> Gemini Decision scores text, images, audio, video and PDFs without generating text. Compare input billing, question limits and independent task results.

Updated 2026-11-12 (Australia/Adelaide)

## Quick answers

### What is Gemini Decision 1 by Google DeepMind?

[Gemini Decision 1](<https://decisionmodels.ai/models/gemini-decision>): A multimodal decision API for text, images, audio, video and PDFs.

[Gemini Decision 1 facts](<https://decisionmodels.ai/models/gemini-decision>)

[Source](<https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/>)

### How much does Gemini Decision 1 cost?

[Gemini Decision 1](<https://decisionmodels.ai/models/gemini-decision>): Published price (vendor-reported): Google reports $0.10 per million input tokens; output free. Shared input billed once, plus each question's instructions and criteria

[Gemini Decision 1 facts](<https://decisionmodels.ai/models/gemini-decision>)

[Source](<https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/>)

### Who makes Gemini Decision 1?

[Gemini Decision 1](<https://decisionmodels.ai/models/gemini-decision>): Google DeepMind

[Gemini Decision 1 facts](<https://decisionmodels.ai/models/gemini-decision>)

[Source](<https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/>)

By Google DeepMind · Google announcement: 2026-11-11 · API

A multimodal decision API for text, images, audio, video and PDFs. It returns yes/no probabilities, a choice or a rubric score without generating text. Questions share the input but cannot see each other’s answers; application code combines the results.

## Facts

- Price: Google reports $0.10 per million input tokens; output free. Shared input billed once, plus each question's instructions and criteria · [Compare prices](<https://decisionmodels.ai/pricing>)
- Inputs: Google reports support for text, images, audio, video and PDFs; the 262,144-token context includes shared input and all questions
- Questions: Google reports up to 1,000 independent questions per request; 2 to 255 choice options or ordered score levels
- Access: Gemini API in Google AI Studio, including a no-cost prototyping tier; listed on OpenRouter
- Limits: No text generation, function execution, caching or Batch API support. Google reports yes/no probabilities from 0.01 to 0.99
- Media billing: Google’s launch lists no separate audio transcription or OCR charges

## Claims and sources

- **VENDOR-REPORTED**: Google reports 150 to 250 ms end-to-end latency for inputs up to 16K tokens, nearly flat from 1 to 100 questions. Those measurements do not cover the maximum context or question count. [source](<https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/>)
- **INDEPENDENT**: Singularity Feed’s independent test asks 1,000 yes/no questions over one 1,000-sentence input. The author reports 92.5% accuracy and median 3.996 seconds across five requests, with estimated cost $0.006743 per request. This tests a shared-input workload, not 1,000 separate documents. [source](<https://github.com/gnana70/gemini-decisions-api-test/blob/main/results/summary.json>)

## Links

- [Source: Launch and billing](<https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/>)
- [Source: API guide](<https://aistudio.google.com/docs/decisions-api>)
- [Source: Model limits](<https://aistudio.google.com/docs/models/gemini-decision-1>)
- [Source: OpenRouter listing](<https://openrouter.ai/google/gemini-decision-1>)
- [Source: Independent test, code and per-answer records](<https://github.com/gnana70/gemini-decisions-api-test>)

## Related projects

No related projects are listed in the registry.