Google's Gemini Decisions API scores 1,000 questions in a single pass
Google DeepMind's new Gemini Decision 1 model powers a Decisions API that evaluates up to 1,000 yes/no, multiple-choice, and rubric-scoring questions against one multimodal input — text, images, audio, video, or PDFs up to 256K tokens. Instead of generating tokens, it scores candidates in one forward pass, returning probabilities and confidence scores in 150–250 ms at $0.10 per 1M input tokens with no output charges. Google teams already use it for model routing, design iteration, emoji selection, and MCP safety checks.
Rather than generating answer text token by token, Gemini Decision 1 scores your candidate options in a single forward pass, returning probabilities and confidence scores in 150-250 ms end-to-end latency at $0.10 per 1M input tokens with zero output tokens billed.
- eminence32
I'm sort of surprised it took Jev for everyone to realize "oh yeah, this is a useful thing that we should have in our product portfolio".
But maybe this is one of those things that's only obvious in retrospect? I'm sure people were trying something similar years ago with grammar-constrained outputs (for example to only output a simple json structure), but you can't get probabilities out of the model that way. Which makes me wonder: how do these models calculate probabilities?
- kodoman
I have still not used a decision model, How are people using them at the moment? is any one using them in a coding harness like Pi?
- 2001zhaozhao
We're about at the point where the AI is now pretty insanely cheap. Passing 100K tokens of context then asking hundreds of questions of 100 tokens each would cost about as much as a single Google search API call.
Out of the hundreds of questions, most of them could even be different variations of the same question to capture more nuance than what is normally possible in a single multiple-choice.
- waximabbax
Its bit more expensive than other other Decision Models in the same lane.
However, it can accept Audio and Video as input as well and for those specific cases it can be extremely useful.
- theanonymousone
The best decision model I have used (besides Jev itself) is respan/span-02, which is based on (finetuned from?) Gemma4 26A4. That makes me optimistic for this release, despite the high cost.