Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocsSettings
Sign in
Continue with GoogleContinue with GitHub
or
Models

Gemini Decision 1

gemini-decision-1by Google

Google's decision-only multimodal model: calibrated yes/no, choice and score answers over text, image, video, audio and PDF input in a single prefill pass, with zero output tokens. Called on POST /v1/decisions (the same request shape as gpt-6-luna-decisions); the gateway translates to Google's Decisions API.

Context

262K

Max output

no data

Price per million tokens

$0.10in$0out

Released

Nov 2026

Waterfall

  1. 1
    Gemini via Experiential Cloud$0.10/$099.9% up--

How to use this model for coding agents

Gemini Decision 1 is a decision helper for your coding agent, not a chat model.

Agent prompt
Add gemini-decision-1 (Gemini Decision 1) as a decision helper/tool for my coding agent.
Keep my coding agent on its current chat model. Gemini Decision 1 answers typed decision questions; it does not generate chat completions.
Write a small native HTTP helper for the OpenAI Decisions API shape, sent to my Experiential gateway:
- POST only to https://api.experientiallabs.ai/v1/decisions.
- Read the Bearer key only from EXPERIENTIAL_API_KEY. If missing, stop and ask me to set it locally; never ask me to paste or log it.
- Do not request an OpenAI or Google API key, and do not call api.openai.com or generativelanguage.googleapis.com.
- Send model "gemini-decision-1" exactly.
Send a JSON request with model, input (text, or messages whose content is input_text and inline base64 input_image parts), and questions (a list). Each question needs instructions and a type, and may carry a unique name:
- predicate: the answer is the probability the statement is true.
- choice: choices lists the allowed values with descriptions; the answer names one value.
- score: levels lists ordered labels with descriptions; the answer is a score.
Use a concise diff and test summary as input, not the entire repository.
Gateway limits: at most 32 questions per request, 64 options per choice, and 2-10 levels per score. These are platform admission bounds, not provider limits.
Request shape reference: https://developers.openai.com/api/docs/guides/decisions
The gateway translates this shape to the model's own decisions API (https://ai.google.dev/gemini-api/docs/decisions-api); choice values must be plain text of at most 128 characters without leading or trailing spaces.
Answers come back in question order; an unnamed question's answer has no name, and a refusal answer means the model declined that question. Read the answer at the review question's position, and show the decision and reported usage to me. Probabilities and confidence are not guarantees of correctness. Never execute a returned choice, merge a change, or bypass review automatically.
Use a bounded timeout, surface HTTP and transport errors, and do not add automatic retries or Idempotency-Key: an unknown outcome may already be charged. This endpoint does not stream and has no Chat Completions, Responses, or Messages facade.
Prepare the helper and a mocked test first. Ask before making a potentially charged live call; do not claim it worked without a real response. Tell me which files you changed.

OpenAI Decisions API guideProvider decisions guide

CapabilitiesAccepts text, image, video, audio, pdf

Sampling

Stop sequences

Streaming

Streaming

Sending an unsupported field? See error referenceGemini docs

Providers serving this model1
Status
Gemini via Experiential Cloudexperientialno datano data99.9%#1 / 1262Kno data$0.10$0no data-no dataactive-
Release notes