Gemini Decision 1 model and Decisions API for fast, calibrated decisions
Google releases gemini-decision-1 in the Gemini API for yes/no, multiple choice and rubric questions at $0.10 per 1M input tokens.
Models:gemini-decision-1
On Zabio today
gemini-3.5-flash-liteLive. Call it by name, or let auto pick it when it fits the job.Price and details
What changed
Google introduced the Gemini Decisions API, powered by the new Gemini Decision 1 model (gemini-decision-1). Instead of generating answer text, the model scores your options in a single forward pass and returns probabilities and confidence scores. You can pass one multimodal input of up to 256K tokens across text, images, audio, video, and PDFs, along with up to 1,000 questions. The question types are yes/no, multiple choice with 2 to 255 choices, and rubric scoring. Latency is 150-250 ms end-to-end, and the price is $0.10 per 1M input tokens with zero output tokens billed. The model is available through the Gemini API in Google AI Studio, with an API no-cost tier for prototyping.
Key details
- Input: one multimodal input of up to 256K tokens across text, images, audio, video, and PDFs
- Up to 1,000 questions per request
- Latency: 150-250 ms end-to-end
- Price: $0.10 per 1M input tokens and $0 for output tokens
- A confidence score from 0 to 1 for every answer
- Available through the Gemini API in Google AI Studio
What it means for Zabio customers
There is no output token charge, so cost depends on input tokens. The shared input is billed once per request, and each question adds only its own instruction and criteria tokens.
Source
Gemini Decision 1 is priced at $0.10 per 1M input tokens and $0 for output tokens, with an API no-cost tier you can use in Google AI Studio for prototyping.
Original announcement: Google AI blog
How it compares
The models in this story next to models of the same class at a similar price, all available with one Zabio key.
| Model | Input, $/M | Output, $/M | Cached, $/M | Context window | 1,000 calls | Analysis and reasoning, hard |
|---|---|---|---|---|---|---|
gemini-3.5-flash-liteGoogleIn this story | 0.30 | 2.50 | 0.03 | 1,000,000 | $1.85 | 75.8 |
qwen3.6-35b-a3bQwen | 0.375 | 2.25 | no data | 262,144 | $1.88 | 83.8 |
glm-4.7Z.ai | 0.40 | 1.75 | 0.08 | 131,072 | $1.68 | 83.3 |
gpt-4.1-miniOpenAI | 0.40 | 1.60 | 0.10 | 1,000,000 | $1.60 | 65.9 |
Prices are the vendor list prices in USD per million tokens. "1,000 calls" is 1,000 requests of 2,000 input tokens and 500 output tokens each, without caching. Zabio bills the list price plus its service fee: see pricing.
Scores: percent correct for that kind of job, aggregated from public results by Epoch AI and LMArena, read on 16 November 2026. Epoch AI: CC BY 4.0, LMArena: CC BY 4.0
Source: Google AI blog (2026-11-11)