Skip to content

SaaS · Analysis

Gemini Decisions API: $0.10 Decisions, No Output Bill

Google's new Decisions API answers yes/no, choice and rubric questions with calibrated probabilities at $0.10 per million input tokens and no output bill. Here is what it costs against Haiku 5.5 and Flash-Lite, and where it fits.

Metarix Editorial · Nov 12, 2026 · 9 min read

Share

Documentation-based research

Gemini Decisions API title card on a blue gradient background
On this page

Google launched the Gemini Decisions API on November 11, 2026. It is a new Gemini API endpoint that answers yes/no, multiple-choice and rubric questions with calibrated probabilities instead of generated text. It runs on a new model, Gemini Decision 1, costs $0.10 per million input tokens and bills zero output tokens.

For anyone running routers, policy checks or LLM graders, this changes the math. Below: what the API does, what it costs against Gemini 3.5 Flash-Lite and Claude Haiku 5.5, where it falls short, and when to use it.

Quick verdict

Use the Decisions API wherever your code asks a model a closed question and then parses the answer: model routing, tool selection, ticket triage, content policy checks and rubric scoring. You get probabilities you can threshold, Google cites 150 to 250 ms latency, and one request can carry many checks for the price of reading the input once. Keep a generative model for anything that needs an explanation, extracted fields or multi-step reasoning. Don't expect big savings over Claude Haiku 5.5 on single questions: the gap is widest against Flash-class models and on many-question requests.

Scroll the table horizontally on smaller screens.

Gemini Decisions API at a glance
ItemDetail
LaunchedNov 11, 2026, Gemini Developer API (v1beta) and Google AI Studio
Model IDgemini-decision-1
EndpointPOST /v1beta/decisions; client.decisions.create in google-genai SDK 3.2+
Question typesYes/no (noul), choice (2–255 options), score (2–255 rubric levels)
Questions per request1 to 1,000, all against one shared input
Context window262,144 tokens across input and all questions
Input typesText, images, audio, video, PDF
Paid price$0.10 per 1M input tokens; output not billed (always 0 tokens)
Free tierYes: 200 RPM, 50,000 TPM, 10,000 requests per day
Not supportedContext caching, Batch API, Flex and Priority inference
Sources: Google AI Studio Decisions API guide, pricing and rate-limit pages, accessed Nov 12, 2026.

What Google shipped

The launch post by Google DeepMind's Min Choi and Felix Yu describes the Decisions API as an endpoint for "fast, closed-set decisions." The Gemini API release notes list it on November 11, one day after Gemini 4 Carbon went GA. The idea is simple. Generative models write text one token at a time, and your code then has to parse that text into a decision. Gemini Decision 1 skips the writing. It scores every candidate answer in a single forward pass and returns numbers.

Three question types

Scroll the table horizontally on smaller screens.

Decisions API question types
TypeUse it forReturns
noul (yes/no)Does a condition hold? Is this a defect? Is the image damaged?Probability of yes, clamped to 0.01–0.99, plus confidence
choicePick one queue, model tier, tool or department from a fixed listTop option, probabilities for all options (sum to 1), confidence
scoreRate against an ordered rubric, such as severity or answer qualityProbability-weighted score, per-level probabilities, legend, confidence
Source: Google AI Studio, Decisions API guide, accessed Nov 12, 2026.

Every answer carries a confidence value, defined as the probability that the top answer is right. Google's guide tells you to set thresholds from labeled examples of your own traffic, weighing false positives against false negatives. The pattern is to act automatically above a threshold and fall back below it.

Diagram of a Decisions API call: shared input and up to 1,000 typed questions go into gemini-decision-1, and code thresholds each answer confidence to act, fall back or escalate
How a Decisions API request flows from shared input to a thresholded action. Graphic: Metarix, based on Google's Decisions API documentation, Nov 12, 2026.

Where it is available

  • Gemini Developer API only, for now. The model page and guide say v1beta only. Google says support for Gemini in Google Cloud is "coming soon."
  • SDKs: Python and JavaScript in google-genai 3.2 or later, plus REST.
  • Third parties: Google says integrations are rolling out across OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode. Check each one's changelog before relying on it.
Google AI Studio's launch post for the Gemini Decisions API, November 11, 2026.

Pricing: why zero output tokens matters

The pricing page lists one paid rate: $0.10 per million input tokens across text, image, video, audio and PDF. Output is "not applicable (0 output tokens)." Two billing rules make that rate go further than it looks:

  • Shared input is billed once. Ask one question or 500 about the same document, and the document is counted once. Each question only adds its own instruction and criteria tokens.
  • No thinking or output bill. There are no thinking tokens and no output tokens, so the cost of a request is fixed by its input. With a generative model, a verbose answer or a long reasoning trace can multiply the bill.

There are also catches. There is no context caching, so a long system context repeated on every call is billed in full each time. There is no Batch API or Flex tier either, so you can't halve the price for offline jobs, as you can with most Gemini and Claude models.

Cost per million requests, compared

Per-token prices only make sense next to the alternatives people use today: a small generative model returning JSON. We worked through two typical workloads at list prices from Google's pricing page and Anthropic's pricing page. Prices as of Nov 12, 2026. This is arithmetic, not a test. Different tokenizers count the same text differently, and real prompts carry system and tool overhead.

Bar chart of list-price cost per one million classification requests for Gemini Decision 1, Claude Haiku 5.5 and Gemini 3.5 Flash-Lite in two scenarios
List-price cost per 1 million requests in two illustrative workloads. Graphic: Metarix, calculated from Google AI Studio and Anthropic pricing pages, Nov 12, 2026.

Scroll the table horizontally on smaller screens.

List-price cost per 1 million requests (illustrative)
WorkloadGemini Decision 1Claude Haiku 5.5Gemini 3.5 Flash-Lite
Per-token price (input / output per 1M)$0.10 / $0$0.10 / $0.50$0.30 / $2.50
A: router, 1,500-token input, 3 questions (~60 output tokens for generative models)$168$198$654
B: policy check, 2,000-token input, 20 rules (~300 output tokens for generative models)$320$470$1,710
Batch discount availableNoYes, 50%Yes, 50%
Context cachingNoYesYes
Metarix calculation from Google AI Studio pricing and Anthropic Claude pricing pages, prices as of Nov 12, 2026. Haiku 5.5 prices are for prompts up to 100,000 tokens. Assumes about 60 tokens per question for instructions and criteria, and no thinking tokens for the generative models. Batch pricing is not supported for Gemini Decision 1.

Two things stand out. Against Gemini 3.5 Flash-Lite, the Decisions API is roughly four to five times cheaper in both scenarios, in line with Google's own "nearly 5x" claim. Against Claude Haiku 5.5, which has the same $0.10 input price, the gap is small: 15% in the router case and about a third in the policy case. Haiku's batch discount would flip it for offline work that can wait. If cost is the only reason to switch, run your own numbers first.

The bigger savings come from avoiding thinking tokens. A reasoning model that writes a few hundred thinking tokens before a one-word label costs far more than either column above. Our cost per successful task guide explains why routing small decisions away from expensive models matters.

What Google claims on quality and speed

These are Google's numbers from the launch post. We haven't verified them, and Google didn't publish per-benchmark scores or name the comparison models in the post.

Scroll the table horizontally on smaller screens.

Vendor claims for Gemini Decision 1
ClaimGoogle's figure
LatencyMedian 50–100 ms model compute, 150–250 ms end to end, for inputs up to 16K tokens
ScalingLatency "nearly flat" from 1 to 100 questions per request
Quality"Leads across the suite" on agent routing, reasoning, ranking and multimodal benchmarks, with the lowest calibration error
CostNearly 5x cheaper across Google's benchmark suite than Gemini 3.5 Flash-Lite via the Interactions API
In productionGemini Notebook uses it as a model router; Google cites up to 40% lower latency on everyday queries
Source: Google, Gemini Decisions API launch post, Nov 11, 2026. Vendor claims, not independently reproduced.

The calibration claim matters most. A raw LLM probability is often overconfident, which makes thresholds unreliable. If Decision 1's probabilities are well calibrated on your data, a 0.9 really means about nine in ten correct, and you can set an auto-approve line with known error rates. Test that on your own labeled set before trusting it.

Limits and gotchas

Scroll the table horizontally on smaller screens.

Decisions API limits
LimitValue
Questions per request1 to 1,000 (bounded by the context window)
Options per choice / levels per score2 to 255 (2 to 10 recommended for rubrics)
Question keys1–64 characters, [A-Za-z0-9_-]
Inline mediaUp to 100 MB per request (50 MB for PDFs); external URLs up to 15 MB
Free tier200 RPM, 50,000 TPM, 10,000 RPD
Tier 1 / Tier 2 / Tier 31,500 / 5,000 / 15,000 RPM; 1M / 4M / 10M TPM
Sources: Google AI Studio Decisions API guide and rate-limits page, accessed Nov 12, 2026.
  • Choice keys are sorted alphabetically. The API reorders options by key, and ties go to the first key. Google advises against keys like none_of_the_above. Use "other" with a clear description instead.
  • Choice always picks something. Probabilities across options always add up to 1, even when nothing fits. Pair choice questions with a yes/no scope check, or threshold confidence.
  • Yes/no tops out at 0.99. A threshold above 0.99 never fires.
  • Score averages level indices. A score of 1.12 can hide a split between levels. Read the per-level probabilities and keep scales linear.
  • Questions can't see each other. For a dependent decision, send a second request or ask both and ignore one answer.
  • Input is untrusted. Google warns that user text can argue for its own classification. Keep a human or second check on payouts and other high-stakes actions.
  • No conversation history blocks. Multi-turn context has to be serialized as text, and tool-call and thought blocks are rejected.

What it looks like in code

An illustrative router that picks a model tier and checks scope in one call, based on Google's documented request shape. It was not run for this article.

# Illustrative only: route a request with one Decisions API call
from google import genai
client = genai.Client(http_options={"api_version": "v1beta"})
result = client.decisions.create(
model="gemini-decision-1",
input=user_message,
questions={
"in_scope": {"type": "noul",
"instructions": "Is this a question about our product or account?"},
"tier": {"type": "choice",
"instructions": "How much reasoning does answering this need?",
"criteria": {"fast": "Lookup or short factual answer.",
"standard": "Some multi-step explanation.",
"deep": "Debugging, planning or analysis across sources."}},
},
)
a = result.answers
if a["in_scope"].noul < 0.5:
model = "refuse_or_redirect"
elif a["tier"].confidence >= 0.7:
model = {"fast": "flash-lite", "standard": "flash", "deep": "carbon"}[a["tier"].choice]
else:
model = "flash" # unsure: take the middle tier

The same pattern works as a cheap first-pass grader. Our LLM-as-a-judge guide covers rubric design. The Decisions API's score type fits narrow, well-defined rubric checks, while open-ended critiques still need a generative judge that explains itself.

Who should switch, and who shouldn't

Scroll the table horizontally on smaller screens.

When to use the Decisions API
WorkloadRecommendationWhy
Model or tier routing in front of every requestUse itLow latency, fixed cost, confidence for fallbacks
Many policy rules over the same inputUse itInput billed once for up to 1,000 rules
Tool selection and stop/escalate checks in agentsUse itClosed choices with thresholds
Image, audio or video triageUse itNative multimodal input, no separate OCR or transcription bill
Overnight bulk labelingCompare firstNo batch discount; Haiku 5.5 or Flash-Lite on Batch may be cheaper
Extraction into JSON fieldsDon'tUse structured output from a generative model
Answers that need an explanationDon'tIt returns numbers, not reasons
Google Cloud-only shopsWaitNot yet on Gemini in Google Cloud
Recommendations by Metarix based on Google's Decisions API documentation and pricing, Nov 12, 2026.

If you run traffic through a gateway, check that it passes the new endpoint before you build on it. Our AI gateways comparison covers the main options, and OpenRouter is on Google's list of integrations rolling out.

Verdict

The Decisions API is the most useful kind of launch: a narrow tool for a job most AI apps already do badly. Teams route, triage and grade with general-purpose models and then parse text, paying for output tokens they don't need. Gemini Decision 1 returns probabilities instead, in a fraction of a second, with the input billed once however many questions you ask.

Our advice: move routing, scope checks and multi-rule policy checks to the Gemini Decisions API first, since they gain most from flat latency and one-time input billing. Validate calibration against a few hundred labeled examples before setting auto-approve thresholds. Keep Claude Haiku 5.5 or Flash-Lite on Batch for bulk offline labeling until you've compared the bills. And keep a generative model for any decision someone will ask you to explain. For more of Google DeepMind's recent pricing moves, see our Gemini 4 Carbon pricing analysis.

Sources

Tools covered in this article

Frequently asked questions

How much does the Gemini Decisions API cost?
Gemini Decision 1 costs $0.10 per million input tokens on the paid tier, and output is not billed because the model always returns zero output tokens. The shared input is billed once per request no matter how many questions you ask. There is also a free tier for prototyping in Google AI Studio.
What is the difference between the Decisions API and structured output?
The Decisions API returns calibrated probabilities for yes/no, multiple-choice and rubric questions without generating text. Structured output asks a generative model to write JSON that follows your schema. Use the Decisions API to route, check or score, and structured output to extract values or write explanations.
How many questions can one Decisions API request include?
Between 1 and 1,000 questions, all evaluated independently against one shared input. The total of the input and all question text must fit in the 262,144-token context window. Questions cannot see each other's answers.
Is the Gemini Decisions API available on Google Cloud?
Not yet. At launch on November 11, 2026, it is available on the Gemini Developer API (v1beta) through Google AI Studio. Google says support for Gemini in Google Cloud is coming soon.
Does the Decisions API support batch or caching discounts?
No. Google's documentation says the Decisions API does not support context caching, the Batch API, or Flex and Priority inference, so repeated input across requests is billed in full each time.

Share

Keep Reading