Google Launches Gemini Decisions API Charging $0.10 per Million Input Tokens with 150-250 ms End-to-End Latency

Google has launched the Gemini Decisions API, a new endpoint powered by its Gemini Decision1 model, designed to help AI agents make quick preset decisions without generating lengthy text responses. {#quote_GOOG}

The interface allows developers to evaluate up to 1,000 independent questions against shared multimodal inputs that include text, images, audio, video, and PDFs. Gemini Decision1 does not generate responses token by token; instead, it scores preset options in a single forward pass, returning probabilities and confidence scores with an end-to-end latency of 150 to 250 milliseconds.

Google states that the model is built for bounded tasks, such as selecting tools, checking policy compliance, routing queries to the correct model, and evaluating context. Developers can submit "yes or no" checks, multiple-choice questions with up to 255 options, or scoring requests based on preset criteria in a single API call.

Faster, Lower-Cost Decisions

According to Google, the median model computation time for the API is 50 to 100 milliseconds, with performance remaining nearly constant when processing 1 to 100 questions per request.

The model supports a context window of up to 256,000 tokens and can handle multiple types of data simultaneously. This allows developers to combine inputs such as audio recordings, images, and documents without relying on separate processing systems.

Google also claims that in benchmark tests covering agent routing, reasoning, ranking, and multimodal understanding, the model outperformed competing systems while achieving the lowest calibration error.

The company states that Gemini Decision1 is nearly five times cheaper than using the Interactions API with Gemini 3.5 Flash-Lite in its shared benchmark suite.

This release comes amid increasing competition in specialized AI decision-making tools. OpenAI launched its Decisions API in October, powered by its GPT-6 Luna model. The company claims that the decision speed of this service is ten times faster than its Responses API and supports up to 400 questions per request. Similar to Google's product, it offers probability-based checks, multiple-choice selections, and scoring based on criteria, priced starting at $0.10 per million input tokens.

The Decisions API charges $0.10 per million input tokens, with no fees for output tokens. Developers pay a single fee for shared input data regardless of how many questions are evaluated, although each question adds tokens related to instructions and criteria.

Empowering Real-World AI Applications

Google has already deployed this technology in several products, demonstrating how dedicated decision models can enhance the speed and efficiency of automated systems.

In Gemini Notebook, the API routes incoming queries to the appropriate model tier and reasoning level. According to Google, this approach can reduce the latency of everyday queries by up to 40%, while reserving more powerful reasoning models for complex tasks.

The technology also supports rapid design experiments on Google Stitch, allowing users to generate interactive product wireframes and make changes via voice commands or touch input.

Meanwhile, Google’s CC Assistant uses the API to select emoji reactions from over 200 options in a fraction of a second.

Google Search is also utilizing this technology as a safety layer to detect adversarial behavior involving Model Context Protocol (MCP) tools.

In addition to these applications, the API can help developers build systems that automatically select the appropriate tools, evaluate incoming information, and determine when human intervention is needed.

The Decisions API is now available through Google AI Studio, which includes a free tier for prototyping. Google is also launching integrations with developer platforms such as OpenRouter, LangChain, Vercel, LiteLLM, and Pydantic AI.