# Gemini Decisions API: Fast, calibrated multimodal decisions

Source: [Google](https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/)  
Feed7 permalink: https://feed7.dev/p/gemini-decisions-api-1mpdjb7  
Published: 2026-11-11T18:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Gemini Decisions API scores up to 1,000 bounded questions on shared multimodal input, giving coding agents a low-latency option for routing, policy checks, and context grading.

## Source Summary

Google’s **Gemini Decision 1** scores up to **1,000 questions** in one pass over shared text, image, audio, video, or PDF input. The API returns probabilities and confidence scores for yes/no, multiple-choice, and rubric questions; Google reports **150–250 ms** end-to-end latency and pricing of $0.10 per 1M input tokens with no output-token charge.

## Practical Implication

For coding agents, consider it for bounded decisions such as tool selection, model routing, policy checks, or grading context. A confidence score can help route uncertain cases to a fallback or human review, while one shared input can support several checks.

## Agent-Ready Context

Google’s **Gemini Decision 1** scores up to **1,000 questions** in one pass over shared text, image, audio, video, or PDF input. The API returns probabilities and confidence scores for yes/no, multiple-choice, and rubric questions; Google reports **150–250 ms** end-to-end latency and pricing of $0.10 per 1M input tokens with no output-token charge.

For coding agents, consider it for bounded decisions such as tool selection, model routing, policy checks, or grading context. A confidence score can help route uncertain cases to a fallback or human review, while one shared input can support several checks.

The latency and cost comparisons are Google’s claims; the material does not include independent results or details about how these figures vary in production. The API is available through Google AI Studio, with broader integrations rolling out.

## Connected Context

Feed7 judgment across 1067 accumulated Signals:

This adds a direct Google API option for bounded agent decisions, with batch questions over shared multimodal input and returned probabilities and confidence scores. It makes confidence-based fallback a concrete integration possibility alongside specialized routers, while the latency and price figures remain vendor claims rather than independent evidence.

- [Jev is the fastest-adopted model in AI Gateway history](https://feed7.dev/p/ai-gateway-jev-model-launch-0rvbmm3) — Both describe probabilistic decision components for routing or guardrails; this signal specifies multimodal batch input and confidence outputs, but neither source establishes comparative decision quality.
- [Gemini Decision 1 now available on AI Gateway](https://feed7.dev/p/gemini-decision-1-now-available-on-ai-gateway-0i56m75) — The Gateway listing makes the same model selectable through Vercel, while this source describes Google's API capabilities and its reported latency and pricing; together they distinguish access route from model behavior claims.

## Context Map

- Layer: tools
- Domains: coding
- Topics: agent-sdks, tool-use, model-selection

## Uncertainty

- The latency and cost comparisons are Google’s claims; the material does not include independent results or details about how these figures vary in production. The API is available through Google AI Studio, with broader integrations rolling out.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
