Google launches Gemini Decisions API for fast multimodal scoring

Google introduced the Gemini Decisions API, backed by the gemini-decision-1 model and available through the Gemini API in Google AI Studio. Instead of generating answer text token by token, the model scores candidate options in one forward pass and returns probabilities and confidence scores. A single request can include text, images, audio, video or PDFs of up to 256K tokens, along with up to 1,000 independent questions.

Three question types are supported: noul for yes/no checks, choice for picking one of 2 to 255 options, and score for grading against an ordered rubric. Every answer carries a confidence score from 0 to 1, so code can send ambiguous cases to a fallback or a human reviewer. Google reports 150-250 ms end-to-end latency and says the model was nearly 5x cheaper than Gemini 3.5 Flash-Lite with the Interactions API across its shared benchmark suite.

Gemini Decision 1 costs $0.10 per million input tokens, and the shared input is billed once per request no matter how many questions are asked. A no-cost tier is available in Google AI Studio for prototyping. Ecosystem integrations are rolling out with OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode, and support in Gemini in Google Cloud is coming soon.

Developers can replace some generative calls used for routing, policy checks or content grading with one scoring request that is billed on input tokens only. The confidence scores give a clear point to escalate uncertain results to a fallback path. Check whether your pipeline needs free-form text output first, because this endpoint returns choices, scores and probabilities rather than generated answers.