Google announces "Gemini Decisions API" specialized in choosing answers from options, returning probabilities instead of generating answers
Google announced the "Gemini Decisions API," specialized for purposes such as tool selection and condition determination where answers are chosen from options. Using a dedicated model, it evaluates multimodal inputs such as text and images in a single inference and returns probabilities and confidence scores. It operates faster and more cheaply than conventional models, marking a full-scale entry into the decision-specialized AI market where other companies are ahead.
Google announced the "Gemini Decisions API," which is specialized for purposes such as tool selection and condition determination where answers are chosen from options. Instead of generating answers, the API returns probabilities.
Using a dedicated model, it evaluates multimodal inputs such as text and images in a single inference and returns probabilities and confidence scores. The company says it operates faster and more cheaply than conventional models.
This marks a full-scale entry into the decision-specialized AI market where other companies are ahead.
This item is a summary. The full, checkable version is at the original source:
Read the original at ITmedia AI+ ↗