Gemini Decision 1
AvailableGoogle DeepMind's decision model behind the new Gemini Decisions API (model ID gemini-decision-1), released Nov 11 2026 through the Gemini API (v1beta) in Google AI Studio. Instead of generating text, it scores up to 1,000 independent yes/no, multiple-choice (2 to 255 options) and ordered-rubric questions against one shared input in a single forward pass, returning calibrated probabilities and a confidence score for each. Natively multimodal input (text, images, audio, video, PDFs) up to 256K tokens. Google cites 150-250 ms end-to-end latency. Priced at $0.10 per 1M input tokens with no output tokens billed, plus a no-cost tier in AI Studio. Joins TypeSafe's Jev and OpenAI's GPT-6 Luna in the decision-model category. Proprietary; size not disclosed.
Specifications
- License
- Proprietary Β· Proprietary
- Weights
- Not released
- Architecture
- unknown
- Parameters
- Undisclosed
- Context window
- β tokens
- Max output
- β
- Knowledge cutoff
- β
- Price (in / out, $/M)
- $0.1 / $0
- Modalities
- TextVisionAudioVideo
Benchmarks
No benchmark scores recorded yet. Spotted some? Submit a correction.
Vendor-reported figures are claims until independently verified. See methodology.