Google launches Gemini Decisions API powered by Decision 1
According to a post by Sundar Pichai on X, Google launched the Gemini Decisions API using the Gemini Decision 1 model for closed-set choices across text, images, audio, video, and PDFs with yes or no, multiple choice up to 255 options, and rubric scoring, priced at $0.10 per 1M input tokens with free output tokens and reporting leading benchmark results with lowest calibration error.
SourceAnalysis
Google launched the Gemini Decisions API powered by the new Gemini Decision 1 model in Google AI Studio, according to Sundar Pichai's announcement. The model handles closed-set choice scoring for up to 1,000 questions across text, images, audio, video and PDFs in a single pass rather than generating text token by token.
It supports three decision types including yes/no, multiple choice with up to 255 options and rubric scoring, priced at $0.10 per million input tokens with no charge for output tokens, which is approximately five times cheaper than Flash-Lite. The model leads several benchmark evaluations with the lowest calibration error, and internal Google teams are already using it for tasks such as rapid product flow design in tools like Stitch.
Sundar Pichai
@sundarpichaiCEO, Google and Alphabet