Google has launched the Gemini Decisions API, a new endpoint powered by its Gemini Decision 1 model that helps AI agents make fast, predefined decisions without generating lengthy text responses.

The interface allows developers to evaluate up to 1,000 independent questions against a shared multimodal input containing text, images, audio, video, and PDFs. Instead of generating responses token by token, Gemini Decision 1 scores predefined options in a single forward pass, returning probabilities and confidence scores with an end-to-end latency of 150–250 milliseconds.

Google said the model is built for bounded tasks such as selecting tools, checking policy compliance, routing queries to the right models, and grading context. Developers can submit yes-or-no checks, multiple-choice questions with up to 255 options, or scoring requests based on predefined rubrics in a single API call.

According to Google, the API delivers a median model computation time of 50–100 milliseconds, with performance remaining nearly unchanged when processing between one and 100 questions per request. 

The model supports a context window of up to 256,000 tokens and can process 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 the model outperforms competing systems across benchmarks covering agent routing, reasoning, ranking and multimodal understanding, while achieving the lowest calibration error.

The company said Gemini Decision 1 is nearly five times cheaper than Gemini 3.5 Flash-Lite using the Interactions API across its shared benchmark suite.

Source link