Reported News
Google launches the Gemini Decisions API and Gemini Decision 1 for fast yes/no, choice and rubric scoring
Google launched the Gemini Decisions API on Nov 11, 2026, powered by a new model, Gemini Decision 1, that "scores your candidate options in a single forward pass" instead of generating text. Google prices it at $0.10 per 1M input tokens with no output tokens billed, and says one request can carry up to 1,000 questions.
- Changes reported
- 5
- listed below, each from a source we read
- We tested
- Not tested yet
- reported from sources; we did not run it ourselves
- Gaps we flag
- 5
- things we could not verify
- Sources
- 1
- 1 primary, linked below
What changed
| # | What the source says | Status |
|---|---|---|
| 01 | The Decisions API is a new Gemini API endpoint for closed-set decisions such as tool selection, policy checks, model routing and context grading, powered by a new model, gemini-decision-1, available in Google AI Studio, according to Google's announcement. | Reported |
| 02 | One request takes a single multimodal input (text, images, audio, video and PDFs, up to 256K tokens) plus up to 1,000 independent questions, and the shared input is billed once per request no matter how many questions are asked, Google says. | Reported |
| 03 | Three question types can be mixed in one request: yes/no checks, multiple choice across 2 to 255 options with normalized probabilities for every candidate, and ordered rubric scores; every answer carries a confidence score from 0 to 1 so code can send ambiguous cases to a fallback or a human. | Reported |
| 04 | Google quotes 150-250 ms end-to-end latency (50-100 ms of model compute) that stays nearly flat from 1 to 100 questions per request, and says the setup is nearly 5x cheaper on its shared benchmark suite than Gemini 3.5 Flash-Lite with the Interactions API. | Reported |
| 05 | Pricing is $0.10 per 1M input tokens and $0 for output, with a no-cost tier for prototyping in AI Studio; Google says integrations are rolling out across OpenRouter, LangChain, Vercel, LiteLLM, Pydantic AI, Pipecat, LiveKit and OpenCode, with Gemini in Google Cloud support coming soon. | Reported |
reported by the sourcemeasured or run by usnot verified
Primary source: Google blog: Gemini Decisions API announcement. We are the fast, independent index; the vendor’s own page is the source of record for this release.
In the source’s words
“Rather than generating answer text token by token, Gemini Decision 1 scores your candidate options in a single forward pass”
“Gemini Decision 1 is priced at $0.10 per 1M input tokens and $0 for output tokens”
What we have not verified
- We did not call the Decisions API; the latency, calibration and cost figures are Google's own claims on its own benchmark suite.
- Google's post says Gemini Decision 1 leads its benchmark suite with the lowest calibration error, but it does not name the competing models or publish the scores in the announcement text we read.
- The latency figures are stated for inputs up to 16K tokens; Google does not give latency for inputs near the 256K limit.
- Google's example code uses the v1beta API version, and the post does not give rate limits, the no-cost tier's quotas or a general-availability date.
- We did not confirm that each listed third-party integration (OpenRouter, LangChain, LiteLLM and the rest) is live; Google says they are rolling out.
This brief is Reported: written from the sources below, not from running the release ourselves.
Sources
- Google blog: Gemini Decisions API announcementprimary source · fetched 2026-11-12
Related
Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/google-gemini-decisions-api-fast-calibrated-multimodal-decisions.md
Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.
Newsletter
The Weekly Verdict. Free, every Monday.
A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.
Free. Double opt-in. One click to unsubscribe.