Skip to content
Models · Nov 11, 2026

Google launches Gemini Decisions API with new Gemini Decision 1 model for fast, calibrated multimodal decisions

The Decisions API evaluates up to 1,000 questions in a single pass across text, images, audio, video, and PDFs, returning confidence scores with low latency and cost.

Trust78
HypeLow hype

1 source · cross-referenced

ShareXLinkedInEmail
TL;DR
  • Google AI introduced the Gemini Decisions API, powered by the new Gemini Decision 1 model, to enable fast, calibrated multimodal decisions.
  • The API supports yes/no, multiple-choice, and rubric-scoring questions in a single forward pass, with end-to-end latency of 150–250 ms and a cost of $0.10 per 1M input tokens.
  • Gemini Decision 1 processes inputs up to 256K tokens and scales nearly flat in latency from 1 to 100 questions per request.
  • The Decisions API is nearly 5x cheaper than Gemini 3.5 Flash-Lite with the Interactions API on a shared benchmark suite, according to Google.

Google AI announced the Gemini Decisions API, a new endpoint designed for fast, closed-set decisions powered by the Gemini Decision 1 model (gemini-decision-1). The API is available through the Gemini API in Google AI Studio and targets use cases such as tool selection, policy checks, model routing, and context grading.

The Decisions API accepts a single multimodal input—spanning text, images, audio, video, and PDFs (up to 256K tokens)—along with up to 1,000 independent questions. Unlike traditional models that generate text token-by-token, Gemini Decision 1 scores candidate options in a single forward pass, returning probabilities and confidence scores with an end-to-end latency of 150–250 ms. Inputs are billed at $0.10 per 1M tokens, with zero output tokens charged.

On benchmarks covering agent routing, reasoning, ranking, and multimodal understanding, Google reports that Gemini Decision 1 leads across the suite with the lowest calibration error. The model maintains median latency of 50–100 ms of model compute (150–250 ms end-to-end) across multimodal inputs and contexts up to 16K tokens, and latency remains nearly flat when scaling from 1 to 100 questions per request.

The Decisions API is positioned as nearly 5x cheaper than Gemini 3.5 Flash-Lite with the Interactions API on a shared benchmark suite, according to Google’s internal comparisons. It supports three decision types in one pass: noul (yes/no), choice (multiple-choice), and score (ordered rubric grading), each returning confidence scores to help route ambiguous cases to fallback or human review.

The API leverages Gemini’s native multimodal architecture, allowing users to combine modalities in a single shared input—such as pairing a call recording with account metadata or a scanned PDF claim with damage photos—and tune resolution on image and video inputs to balance visual detail and token cost.

Sources
  1. 01Google AI — Blog — Gemini Decisions API: Fast, calibrated multimodal decisions
Also on Models

Stories may contain errors. Dispatch is assembled with AI assistance and curated by human editors; despite the trust-score filter, mistakes happen. We correct publicly — every article links to its revision history. Nothing here is financial, legal, or medical advice. Verify before relying on any claim.

© 2026 Dispatch. No ads. No sponsorships. No paid placement. Reader-supported via Ko-fi.

Built by a person who cares about honest AI news.