Gemini Decision 1 now available on AI Gateway

Vercel's AI Gateway now offers Google's Gemini Decision 1, a multimodal decision model that accepts text, images, audio, video, and PDF documents and returns Boolean probabilities, choices, and scores without generating output tokens. Developers call it as `google/gemini-decision-1` through the AI SDK, the TypeSafe-compatible API, or the Decisions API; PDF, audio, and video inputs require AI SDK 7, while the TypeSafe-compatible and Decisions APIs support only text and image inputs. Decision calls are logged and counted toward AI Gateway budgets alongside other model requests.

Gemini Decision 1 from Google https://vercel.com/ai-gateway/models/gemini-decision-1 is now available on AI Gateway. The multimodal decision model works with text, images, audio, video, and PDF documents, returning Boolean probabilities, choices, and scores. Use it to route requests, check policies, filter agent tools, or rank results without generating output tokens. Use google/gemini-decision-1 with the AI SDK, TypeSafe-compatible API, or Decisions API. PDF, audio, and video inputs are supported through AI SDK 7. The TypeSafe-compatible and Decisions APIs support text and image inputs. AI Gateway provides a unified way to access models and track usage and cost. Decision calls appear in logs https://vercel.com/docs/ai-gateway/observability-and-spend/logs and count toward budgets https://vercel.com/docs/ai-gateway/observability-and-spend/budgets alongside other model requests. See the decision documentation https://vercel.com/docs/ai-gateway/modalities/decision for Choice, Score, and Boolean questions. To pick a decision model, browse the available models https://vercel.com/ai-gateway/models?modality=decision or read our decision model guides https://vercel.com/i/category/decision-models .