Google Ships Gemini Decisions API

// 1h agoMODEL RELEASE

Google Ships Gemini Decisions API

Google’s Gemini Decisions API introduces Gemini Decision 1, a multimodal model that scores up to 1,000 bounded questions in one pass. It delivers probabilities and confidence scores in 150–250 ms at $0.10 per million input tokens with no output-token charges.

// ANALYSIS

Decision models are becoming a control layer for agents, not another chatbot category.

–One shared input can power routing, policy checks, tool selection, grading, and triage across text, images, audio, video, and PDFs.
–Single-pass scoring avoids token-by-token generation, making latency and cost predictable for high-volume decisions.
–Confidence scores let developers escalate uncertain cases to a larger model or human reviewer instead of blindly trusting automation.
–Strands Decider 2B shows the same pattern can run locally, giving teams a meaningful hosted-versus-self-hosted deployment choice.
–Integrations with LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit, OpenRouter, and OpenCode could make decision models a standard agent primitive.

// TAGS

gemini-decisions-apireasoningmultimodalagenttool-useapiinferencehosted-service

DISCOVERED

1h ago

2026-11-12

PUBLISHED

4h ago

2026-11-12

RELEVANCE

9/ 10

AUTHOR

themuscleai

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE37m ago

Framer Agent Generates Images, Shaders

Framer’s AI Agent can now turn natural-language prompts into generated imagery and interactive shader effects, including pointer-driven smudges, halftones, CRT visuals, bokeh, and pencil styles. The workflow aims to produce polished web interactions without manual code or After Effects.

OPEN SOURCE44m ago

Perplexity Decider v1.3 Adds Locate Extraction

Perplexity open-sourced its latest decision models under Apache licensing, adding Locate for extracting exact text spans and character positions. Both models are free on OpenRouter for one week and support classification, routing, moderation, reranking, and structured evaluation.

LAUNCH49m ago

Daybreak Red Team automates continuous pen tests

OpenAI’s Daybreak Red Team puts coordinated AI agents to work testing web applications, validating vulnerabilities, and checking whether patches actually stop exploits. The early-access service targets organizations that need continuous offensive security coverage without maintaining a dedicated red team.