Skip to content
Main Site News Console

Gemini Decisions API

· Simon Willison Translated
技巧LLM

Gemini Decisions API (via) Google has joined Jev and OpenAI in the decision model space with “Gemini Decision 1”. This new model API is almost identical to Jev: it supports the same three question types (yes/no, multiple choice, and rubric-scoring) and even adopts Jev’s “Noul” terminology for yes/no questions.

It is priced the same as the GPT-6 Luna decision model: 10 cents per million input tokens, with free output. Jev remains the cheapest of the three at 4.2 cents per million tokens.

Jev is text-only (and JSON). OpenAI handles text and images. Gemini Decision 1 is fully multimodal: it covers text, images, audio, video, and PDFs.

I tested its video capabilities by passing it my Yonkers stompy robot video file along with these questions:

dragon: Does this video have a dragon in it?
robot: Does this video have a robot in it?
france: Is this video set in France?
usa: Is this video set in the USA?

Where Jev and OpenAI return 1.0 or 0.0 for yes/no questions, Gemini insists on being a little less confident:

{
"dragon": {
"type": "yes_no",
"probability": 0.04976021841520312
},
"robot": {
"type": "yes_no",
"probability": 0.9234055387792485
},
"france": {
"type": "yes_no",
"probability": 0.08329171353166241
},
"usa": {
"type": "yes_no",
"probability": 0.9230459995157706
}
}