From the source
- Google introduced the Gemini Decisions API on November 11, 2026, an endpoint powered by Gemini Decision 1 that evaluates as many as 1,000 independent questions across text, images, audio, video and PDFs in one request.
- The endpoint is built for bounded judgments such as tool selection, policy checks, model routing, context grading and ranking, rather than prose or explanations.
- Instead of decoding answer text token by token, Gemini Decision 1 scores candidate options in one forward pass, allowing programs to branch, sort and route directly on typed responses.
- The documentation sets a 262,144-token context window covering the shared input and all questions, and requests can mix yes/no checks, fixed-set choices and ordered rubric scores.
- Every answer includes a confidence score from 0 to 1, defined as the estimated probability that the top answer is correct, and the documentation recommends setting thresholds with labeled examples from a developer's own traffic.
- Google reports 50–100 milliseconds of median model-compute latency and 150–250 milliseconds of end-to-end latency across multimodal inputs and contexts up to 16K tokens, with latency nearly flat between one and 100 questions per request.
- Pricing is $0.10 per 1 million input tokens, with zero output tokens billed, and Google describes Gemini Decision 1 with the Decisions API as nearly five times cheaper across the shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API.
- Initial access is limited to the Gemini Developer API v1beta with Gemini Decision 1, and question instructions are text-only, with conversation history, tool-call blocks, context caching, Batch API, and Flex or Priority inference unavailable.