New: AI API Cost Calculator — compare GPT, Claude, Gemini, Grok, Llama, DeepSeek & Kimi pricing live
Developers · News

Google's Gemini Decision 1 Answers 1,000 Questions in One API Call

By ToolsDig Research · Updated November 12, 2026 · How we research

Nothing here is sponsored — no affiliate links on this page. Every fact below comes from Google's announcement of November 11, 2026, as reported by VentureBeat, with independent benchmark context from Artificial Analysis. We have not tested Decision 1 hands-on — nobody outside Google had access before launch day — and this is researched analysis, not hands-on testing.

A glowing decision panel showing scales of balance with checkmarks, on a dark developer desk in deep blue and teal light

Google shipped a model on November 11, 2026 that doesn't write anything. That's the whole point. Gemini Decision 1 is a decision-only model: you hand it one input and up to 1,000 questions, and it scores every option in a single forward pass. No tokens generated, no prose — just probabilities and a confidence score, back in 150–250 milliseconds.

🔍 How we put this together

We used Google's blog post of November 11, 2026 ("Gemini Decisions API: Fast, calibrated multimodal decisions," by Min Choi and Felix Yu), the VentureBeat launch coverage for the benchmark table details, and the Artificial Analysis Decision Index v2.1 as reported by VentureBeat for the independent view. Where something is a vendor claim, we say so.
🏆 Verdict: The price and the calibration are the story. At $0.10 per million input tokens with zero output cost, Decision 1 collapses the most common agent expense — the judgment call — into a 200 ms scored pass. Its calibration error of 0.0250 is genuinely strong. But the independent index ranks it ninth of 18, so run your own eval on your own labeled data before swapping out your router.

What it is

Most of an agent's LLM calls aren't really generation. They're judgments wearing a generation costume: which tool should run, is this output safe to show, which model should handle this query, how good is this retrieved chunk. Each one costs a full decode — tokens out, latency, money — for an answer that could have been a number.

The Decisions API strips that down. One request carries a shared multimodal input — text, image, audio, video, PDF, up to 256K tokens — plus 1 to 1,000 independent questions. Three question types:

Every answer includes a confidence score from 0 to 1, so your code can route ambiguous cases to a fallback or a human reviewer. The shared input is billed once per request no matter how many questions you ask — each question only adds its own instruction and criteria tokens.

The endpoint is POST https://generativelanguage.googleapis.com/v1beta/decisions with x-goog-api-key auth, or client.decisions.create in the google-genai SDK (3.2+). It is live in the Gemini API and Google AI Studio. Integrations are rolling out across OpenRouter, LangChain, Vercel AI SDK, LiteLLM, Pydantic AI, Pipecat, LiveKit, and OpenCode.

The price is the real story

$0.10 per million input tokens. $0 for output — because there is none. There is a no-cost tier in AI Studio for prototyping.

Google says that is nearly 5x cheaper across its shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API. That is Google's claim, on Google's suite — but the direction is right. The expensive part of a judgment call was never the input. It was paying for a model to think out loud in tokens you didn't need.

Do the math on your own stack: if your agent makes 20 judgment calls per task and each one currently costs a 200-token generation, Decision 1 collapses that to one scored pass. The latency claim is the other half of it — 50–100 ms of model compute, 150–250 ms end-to-end, nearly flat from 1 to 100 questions per request, at contexts up to 16K tokens. That is the number that makes it usable as a control plane, not just a batch scorer.

The benchmarks, and the asterisks on them

Google's launch table compares Decision 1 against TypeSafe Jev 1.14, OpenAI's GPT-6 Luna (via the OpenAI Decisions API), and Gemini 3.5 Flash-Lite across nine benchmarks. Decision 1 leads 7 of the 9 — and 5 of the 7 tests that all four models ran.

The headline numbers, all Google's own:

BenchmarkGemini Decision 1GPT-6 LunaJev 1.14
JevBench (public split)92.2%90.9%90.0%
Top-1 calibration error (lower is better)0.02500.07210.0494

The calibration gap is the most interesting number in the table. A calibration error of 0.0250 — roughly half of Jev's 0.0494 — means when the model says it is 80% sure, it is right about 80% of the time. That is what makes confidence scores usable as routing logic instead of decoration. If you are building human-escalation rules on top of this, calibration matters more than raw accuracy.

But Google lost two of the nine, and those two are worth naming: Jev beats Decision 1 on Mind2Web Multimodal (86.8% vs 86.2%) and on When2Call, the test of knowing when to invoke a tool (82.0% vs 79.9%).

And the independent scoreboard is less flattering still. The Artificial Analysis Decision Index v2.1 puts Gemini Decision 1 ninth of 18 at launch, with a score of 65.98 — just behind Jev 1.14 at 66.23, and well behind Drex Max v1.1 at 72.62. On the index's AA-Paperclip test, which requires correctly understanding entire documents, only 33% of documents were answered completely correctly, versus 63% for Drex Max.

So the honest read: Google's model is very good at the benchmarks Google chose, genuinely well-calibrated, and merely mid-pack on the one independent index that exists. Both things are true at once.

Google is late, and it knows it

This is a race Google is joining, not leading. OpenAI's Decisions API went generally available on October 22 with GPT-6 Luna. Amazon shipped Strands Decider 2B in October. TypeSafe's Jev arrived in September. Microsoft has Decision-1 too. Every major lab now has a model that judges instead of writes.

Google's counter is that it is already dogfooding it: Gemini Notebook uses the Decisions API as a real-time router, directing queries to the right model tier and thinking level, with up to 40% lower latency on everyday queries. Google Search uses it as a safety layer for MCP tools. Stitch's rapid canvas experiment uses it to generate playable wireframes. CC from Google Labs uses it to pick emoji reactions from a 200+ palette in a fraction of a second. Those are real internal deployments, not demo slides — and the Notebook one is the most telling, because routing is exactly the job this model exists for.

It also landed a day after Gemini 4 Carbon went generally available to paying users. Google is shipping fast right now. That doesn't make each launch good, but the pace itself is the context.

The catches

What we'd actually do

If you run agents in production, the use cases that justify trying this today are narrow and concrete: tool selection, policy checks, model routing, context grading — the small judgments your agent makes dozens of times per task. That is where a 200 ms scored call at $0.10 per million tokens replaces a full generation, and the savings compound.

Don't rip out your existing router this week. Pick one judgment in your agent loop — the one you already have labeled data for — and run Decision 1 against your current approach for a day. The calibration number is the thing to check, not the accuracy. If the confidence scores track reality on your data, you have a router. If they don't, you have a launch-day benchmark.

And if you are on Vertex AI, or you need the model to explain itself, this isn't your launch. Wait for the Cloud support date and watch whether the independent index moves.

What we don't know yet

Sources: Google blog, "Gemini Decisions API: Fast, calibrated multimodal decisions" (Nov 11, 2026); VentureBeat, "Google's Gemini Decision 1 model scores up to 1,000 questions in one API call" (Nov 11, 2026); Artificial Analysis Decision Index v2.1 as reported by VentureBeat. Benchmark figures are Google's own except where the independent index is cited.