Skip to content

Model detail

Gemini Decision 1

Provided by Google
Pay-as-you-go

Gemini Decision 1 evaluates typed yes/no, choice and rubric questions over shared multimodal input and returns calibrated probabilities without generating output tokens.

Model specs

Model ID
gemini-decision-1
Context length
262.144K
Max output
–
I/O modalities
Released
2026-11

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • Gemini /v1beta/models/{model}:generateContent POST
  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Pricing updated

Input

$0.1000 /1M Tokens

Completion

$0.4000 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Decisions

Gemini Decision 1 is Google's decision model for state-and-question decision tasks. It accepts input such as text, image and video, and returns decisions. Its capabilities are broken down in the section just below. Send one state-and-question request with your own options and accumulated state before you wire it in.

What should you check before using it?

262,144 tokens of state and questions

Gemini Decision 1 accepts up to 262,144 tokens of state and questions per request. Size your accumulated state and questions against that window before each request.

Why use it through MixRoute?

Call this model with a MixRoute API key

Use /v1beta/decisions with model ID gemini-decision-1 through MixRoute at https://api.mixroute.ai. Configure a client for this endpoint, then test the integration with a sample request before sending production traffic.

07

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Available:

Vision input

Gemini Decision 1 can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

This model has no cache-read price; caching is not counted

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.