Google: Gemini Decision 1 API
Gemini Decision 1 is Google's specialized multimodal model for the Decisions API: it answers yes/no, choice and rubric score questions over text, images, audio, video and PDFs, up to 1,000 per request, with calibrated probabilities and zero output tokens.
- Context window: 262,144 tokens
- Input: text, image, audio, video, file
- Output: text
- File input: Supported
- Released: 2026-11-11
Frequently Asked Questions
What is the context window of Gemini Decision 1?
Gemini Decision 1 supports a context window of up to 262,144 tokens.