Google introduces Gemini Decisions API for fast, calibrated multimodal decisions

Google launches the Gemini Decisions API, powered by the Gemini Decision 1 model (gemini-decision-1), for fast, closed-set decisions across multimodal inputs.
The API evaluates up to 1,000 independent questions in a single forward pass, returning probabilities and confidence scores with 150-250 ms end-to-end latency.
Priced at $0.10 per 1M input tokens with zero output token charges, the service is nearly 5x cheaper than Gemini 3.5 Flash-Lite with the Interactions API across shared benchmarks.
Gemini Decision 1 leads benchmarks for agent routing, reasoning, ranking, and multimodal understanding while maintaining the lowest calibration error.

Capabilities and Pricing

Supports three decision types in one request: yes/no (noul), multiple choice (2 to 255 options), and ordered rubric scoring.
Accepts multimodal inputs including text, images, audio, video, and PDFs up to 256K tokens, with shared input billed once per request.
Median model compute latency is 50-100 ms, remaining nearly flat from 1 to 100 questions per request.

Available now in Google AI Studio with a no-cost tier for prototyping, alongside Python, JavaScript, and REST documentation.
Internal Google teams use the API for dynamic model routing in Gemini Notebook, rapid design iteration in Stitch, emoji selection in CC, and safety checks for MCP tools in Search.
Ecosystem integrations are rolling out across OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit, and OpenCode, with Google Cloud support coming soon.