Catch up: @GoogleAIStudio launched the Gemini Decisions API. Gemini Decision 1 scores up to 1,000 yes/no, choice or rubric questions in one pass, at $0.10 per 1M input tokens and $0 for output.
The fine print is in Google's own chart.
ALT Google's Gemini Decision 1 demo image: a coffee spill on a kitchen counter labeled Spill detected 0.95, wipe_with_cloth 98% and Minor localized spill 1.19 of 2.
Nov 11, 2026 · 10:16 PM UTC
1
10
Cost: on 7 shared evals, Google's table prices Gemini Decision 1 at $0.88 total. TypeSafe Jev 1.14 came in at $0.68, GPT-6 Luna at $0.93 and Gemini 3.5 Flash-Lite at $4.14.
Much cheaper than Google's own Flash-Lite, but not the cheapest.
ALT Bar chart of total price across 7 shared evals: Gemini 3.5 Flash-Lite $4.14, GPT-6 Luna $0.93, Gemini Decision 1 $0.88, TypeSafe Jev 1.14 $0.68.
1
21
Accuracy: it leads 7 of the 9 key benchmarks shown.
TypeSafe Jev 1.14 wins the other two: Mind2Web Multimodal (86.8% vs 86.2%) and When2Call (82.0% vs 79.9%).
ALT Text poster reading Top on 7 of 9, not all, naming the two benchmarks TypeSafe Jev 1.14 wins.
1
12
Speed: @GoogleDeepMind quotes 150-250 ms end to end, but that median covers inputs up to 16K tokens. A request can carry up to 256K.
It runs on the v1beta Gemini API, so test with your own traffic first.
Follow @BroadwakeAI for more.
ALT Text poster reading Fast, up to 16K tokens, explaining the latency caveat.
1
6
