---
title: "Google Introduces Gemini Decisions API: AI Makes Decisions in 50–100 ms Without Text Generation"
description: "Google introduced the Gemini Decisions API powered by the Gemini Decision 1 model, evaluating data and choosing actions in 50–100 ms across text, images, audio, and video. Output tokens are free, and input tokens cost $0.10 per million."
date: 2026-11-11T21:27:56.414Z
lang: en
url: https://xab.info/en/posts/google-gemini-decisions-api-launch
tags: [google, gemini, ai, api, machine-learning]
author: "Alexander Buran"
publisher: "XAB.info"
---

# Google Introduces Gemini Decisions API: AI Makes Decisions in 50–100 ms Without Text Generation

![Gemini Decisions API interface demonstrating spilled liquid detection on a kitchen countertop](https://xab.info/media/2026/11/11/google-gemini-decisions-api/google-gemini-decisions-api-1.webp)

## Key Points

- Gemini Decisions API, powered by Gemini Decision 1, processes up to 1,000 questions per request with a median latency of 50–100 ms.
- The model handles text, images, audio, video, and PDFs within a 256,000-token context, offering three evaluation modes with a 0–1 confidence score.
- Pricing is $0.10 per million input tokens with no charge for output tokens; the model is nearly 5 times more efficient than Gemini 3.5 Flash-Lite.
- The API is already used in Gemini Notebook, Stitch, and Google Search; keys are available via Google AI Studio with a free tier.

Google has released the Gemini Decisions API, a programming interface designed for tasks where artificial intelligence needs to quickly evaluate data, select actions, and verify specified conditions. At the core of the new solution is the Gemini Decision 1 model, capable of analyzing multiple types of information simultaneously and processing up to 1,000 questions in a single request. According to the developers, this is not just another generative model, but a specialized tool for decision-making where the required output is an evaluation, choice, or numerical metric rather than a detailed response.

### Decision in a Single Pass Instead of Sequential Text

The main difference between the new release and conventional generative models lies in how requests are processed. Instead of sequentially "writing out" text, Gemini Decision 1 evaluates the proposed options in a single pass. As a result, the median computation time is 50–100 ms, and taking full request processing into account, the latency increases to 150–250 ms. This approach makes the model suitable for scenarios where reaction speed is critical rather than the volume of generated text.

### Multimodality and Three Evaluation Modes

The model works with text, images, audio recordings, video, and PDF documents, allowing different data types to be combined within a single context. For example, a phone call recording can be correlated with account information, and an insurance claim scan can be verified alongside vehicle damage photos. The maximum total context reaches 256,000 tokens. The developers have provided three evaluation modes: determining the probability of a statement's truth, selecting the most suitable option from a list, and scoring based on a predefined scale. Each result returns a confidence score from 0 to 1, enabling the application to automatically route doubtful cases to human review — in the demonstration interface, this looks like detecting a spilled liquid with a confidence of 0.95 and recommending the action "wipe with cloth" with a 98% probability.

### Where Google Is Already Applying the New API

The company plans to use the Gemini Decisions API as an intermediate control layer for AI systems. For instance, Gemini Notebook uses it to select the appropriate model and reasoning level depending on request complexity: latency for routine requests is reduced by up to 40%, while deep analysis models are reserved for complex tasks. In the Stitch builder (formerly known as Galileo AI), the technology helps prototype interfaces, and Google Search uses it to detect malicious behavior when interacting with MCP tools.

### Tests, Efficiency, and Pricing

Google provides comparative test results covering request routing, logical reasoning, ranking, and multimodal understanding. According to the developer, Gemini Decision 1 showed the best results in this test suite and minimal calibration error. Under identical test conditions, the model proved to be nearly five times more cost-effective than Gemini 3.5 Flash-Lite with API. Usage costs $0.10 per million input tokens, while output tokens are not billed: the general input data is paid for once regardless of the number of evaluated questions, and additional costs are formed solely by instructions and criteria for each check.

### Developer Access

Developers can already obtain an API key in Google AI Studio and use the free tier to build prototypes. Integrations with OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, and other tools are rolling out gradually, and the company promises to add Gemini support in Google Cloud later. Thus, the Gemini Decisions API is positioned as a cheap and fast "decision layer" that can be embedded into existing AI pipelines without generating redundant tokens.

## Fact-Check & Sources

- [Google научила ИИ принимать решения без лишних слов — Gemini Decisions API сэкономит на токенах](https://3dnews.ru/1151176) - Primary source: description of the API, Gemini Decision 1 model, 50–100 ms latency, three evaluation modes, 256k context limit, $0.10/M input token pricing, and integrations.
- [Google научила ИИ принимать решения без лишних слов — Gemini Decisions API сэкономит на токенах](https://3dnews.ru/1151176/google-nauchila-ii-prinimat-resheniya-bez-lishnih-slov-gemini-decisions-api-sekonomit-na-tokenah) - Duplicate link to the same 3dnews.ru material; the summary matches the core article.

## FAQ

### How does the Gemini Decisions API differ from standard generative models?

Instead of sequential text generation, the Gemini Decision 1 model evaluates options in a single pass, yielding a median latency of 50–100 ms (up to 150–250 ms with full request processing).

### What data types does the model support, and what is the context limit?

The model processes text, images, audio, video, and PDF documents, which can be combined in a single context of up to 256,000 tokens.

### How much does it cost to use the Gemini Decisions API?

Pricing is $0.10 per million input tokens with no fees for output tokens; input data is paid for once regardless of the number of verified questions.

### How can developers get access to the API?

An API key can be obtained via Google AI Studio with a free tier for prototyping; integrations with OpenRouter, LangChain, Vercel, LiteLLM, and Pydantic AI are emerging, with Google Cloud support promised later.