Google launches Gemini Decisions API as Perplexity open-sources Decider v1.3

Google released Gemini Decision 1, a model built only for decisions, along with the Gemini Decisions API. Rather than generating tokens, it scores a closed set of options in a single forward pass for yes/no questions, multiple choice and rubric-based rating. Google says it costs $0.10 per 1M input tokens with no output charge, runs at 150-250 ms latency, and is already used for model routing and agent tool selection.

A DEV Community user reports that Google has released the Gemini Decisions API, powered by a Gemini Decision model and pitched at fast, calibrated multimodal decision tasks, linking to the official blog post. The author says they will test it against Jev for zero-shot classification work.

Google has released Gemini Decision 1 and a companion Decisions API that scores a closed set of options and returns probabilities instead of generating text; Google lists tool selection, model routing and policy checks as intended uses. Pricing is $0.10 per million input tokens with free output, and end-to-end latency is around 150–250ms.

Google has launched the Gemini Decisions API, powered by the new Gemini Decision 1 model, which evaluates inputs against up to 1,000 preset questions at once and accepts text, images, audio, video and PDFs. Google says median end-to-end latency is 150–250 ms for multimodal inputs up to 16K tokens, with input priced at $0.1 per million tokens and output tokens free.

Google has launched the Gemini Decisions API, an AI service built on a new model called Gemini Decision 1 that is designed to answer user questions cost-efficiently, SiliconANGLE reports. Unlike general-purpose LLMs, Gemini Decision 1 has a much narrower focus.

Google released the Gemini Decisions API, powered by the new Gemini Decision 1 model, which scores up to 1,000 independent yes/no or multiple-choice questions over a single multimodal input in one forward pass. It accepts up to 256K tokens across text, images, audio, video and PDFs, returns in 150-250 ms, costs $0.10 per 1M input tokens with output free of charge, and is available in Google AI Studio with a free tier.

According to Simon Willison, Google has launched the Gemini Decision 1 model API, entering the decision model category. It supports three question types and multimodal inputs, priced at 10 cents per million input tokens with free output.

Google has launched the Gemini Decisions API powered by Gemini Decision 1, returning calibrated probabilities for up to 1,000 text, image, audio, video, and PDF questions at $0.10 per 1M input tokens.

According to The Decoder, Google DeepMind has introduced the Gemini Decisions API, enabling the evaluation of up to 1,000 closed-ended questions across text, images, audio, and video in a single pass. Gemini Decision 1 delivers results in 150 to 250 milliseconds at approximately five times lower cost than Gemini 3.5 Flash-Lite.

Google announced the Gemini Decisions API powered by the new Gemini Decision 1 model via Google AI Studio. Instead of generating text token by token, the model scores up to 1,000 closed-set options in a single forward pass and returns probabilities and confidence scores.

Google has launched the Gemini Decisions API, powered by its new Gemini Decision 1 model. Available at $0.10 per 1M input tokens, the API returns predefined yes/no or choice answers with confidence scores.

Google has announced the release of Gemini Decision API, powered by the new Gemini-decision-1 model and now available in Google AI Studio and APIs. The tool delivers fast, calibrated decisions on up to 1000 questions simultaneously across text, images, audio, video, and PDFs.

Gemini Decision 1 achieves the highest scores among decision models in knowledge and reasoning evaluations on the Artificial Analysis Decision Index. It scores 66 on AA-Omniscience-Decision, tying with GPT-6 Luna (Max) and outperforming d1-ultra.

Google has released its first decision model, Gemini Decision 1, which scores 66 on the Artificial Analysis Decision Index v2.1. The model takes the lead in knowledge and reasoning benchmarks among decision systems.

Google has officially introduced the Gemini Decisions API, powered by the latest Gemini Decision model to deliver fast and calibrated multimodal decisions. The API processes complex visual and text inputs for automated decision-making workflows.