Google’s new Decisions API targets fast, high-volume classification, while Gemini 4 Carbon and Antigravity’s multi-agent preview expand its developer tools.
Google’s newest developer release is built for a task that often does not need a fluent answer: making a bounded decision. The Gemini Decisions API, launched Wednesday and powered by Gemini Decision 1, returns probabilities and confidence scores for yes-or-no, multiple-choice and rubric-scoring questions across text, images, audio, video and PDFs.
The API can evaluate as many as 1,000 questions against shared input of up to 256,000 tokens. Google reports latency of 150 to 250 milliseconds and charges $0.10 per million input tokens, with no fee for output tokens. The company says shared input is billed once per request, not once for each question.
That pricing and design could suit developers handling repeated checks against the same material: moderation decisions, document extraction, ranking, policy checks or grading. Instead of paying for a model to generate a separate explanation for each item, an application can request scores and confidence estimates. Google says the system scores candidate answers in a single pass rather than generating text token by token. The practical test for builders will be whether its confidence scores are reliable enough for their particular data and whether a fast, narrow decision is preferable to a general-purpose model’s flexibility.
Developers can try the API in Google AI Studio, which offers a no-cost tier for prototyping. Google says it can also support model routing and tool selection. Those uses still require careful testing: a confidence score is not a guarantee, and automated decisions that affect customers or employees need clear safeguards and a way to review mistakes.
Google also made Gemini 4 Carbon generally available on November 10 through the paid Gemini API tier, Google AI Studio, Android Studio and Gemini for business. The model is rolling out to Google AI Ultra subscribers in Antigravity, the Gemini app and AI Mode in Search. Google describes Carbon as its strongest model for frontier cybersecurity performance and long-horizon capabilities, but that is the company’s characterization; the release details do not establish how it compares with competitors on independent tests.
For software teams, the more immediately testable change may be Antigravity’s preview of `/swarm`. A single prompt can start a coordinated set of agents: a coordinator assigns parallel workers in isolated Git worktrees, while verification agents test changes and challenge diffs. The feature is available through the Antigravity app and CLI.
Separate worktrees offer a practical way to limit collisions between agents, but parallel output is not automatically dependable output. Small teams considering the preview should judge it by review time, test quality and the amount of cleanup required—not by the number of agents. Isolation and verification are useful design choices; human review remains necessary before changes reach production.
There is also a financial signal from the market leader. Bloomberg, as reported by TechCrunch, said OpenAI’s revenue exceeded $10 billion in the three months ending in September, nearly 50% above the previous quarter. The figures were shared with investors and were not public audited results. They suggest strong commercial demand, but do not reveal how much comes from subscriptions, business customers or compute-intensive services.
Taken together, Google’s releases give developers concrete experiments rather than a reason to rebuild their systems overnight. The Decisions API is worth testing where repeated, measurable classifications dominate cost or latency. Carbon and Antigravity’s swarm preview warrant evaluation against existing coding workflows, with attention to quality and oversight. The available announcements do not settle whether these tools will lower the total cost of building software; that depends on how well they perform on real workloads.
Mason Reed serves as a Staff Writer for Just Right News, where he spearheads the Future Frontiers & Special Projects desk. In an era defined by rapid technological shifts and evolving social landscapes, Mason provides a steady, principled voice, examining the innovations of tomorrow through the lens of traditional American values. His work is most prominently featured in his signature series, “The Next Horizon,” where he explores the intersection of emerging technology, national sovereignty, and the preservation of individual liberty.
A native of San Diego, California, Mason’s worldview was shaped by the unique culture of his hometown. Growing up in a region defined by its strong military presence and its history of maritime industry, he developed a deep-seated respect for the institutions that provide national stability and the entrepreneurial spirit that drives the American economy. This upbringing instilled in him a belief that true progress is not found in discarding the past, but in building upon a foundation of proven principles. His reporting often reflects this San Diego influence, emphasizing the importance of a robust national defense and the necessity of maintaining a competitive edge in the global marketplace.
Now based in San Francisco, Mason operates from the heart of the world’s technological engine. Living and working in the Bay Area provides him with a front-row seat to the advancements—and the ideological challenges—emanating from Silicon Valley. While many in the region embrace a “move fast and break things” mentality, Mason’s reporting serves as a vital counterweight. He offers Just Right News readers a “boots on the ground” perspective, documenting how radical local policies and the concentration of tech power impact the everyday lives of citizens. His proximity to the industry allows him to cut through the marketing jargon of big tech to uncover the real-world implications for privacy, free speech, and the nuclear family.
In his “Future Frontiers” beat, Mason tackles complex subjects ranging from the ethics of artificial intelligence to the burgeoning private space race. He approaches these topics with a healthy skepticism toward centralized bureaucracy, championing instead the decentralized innovations that empower individuals. Through “The Next Horizon,” he highlights the pioneers and thinkers who are working to ensure that the future remains a place where human dignity and constitutional rights are protected. He believes that the rapid pace of change requires more than just technical expertise; it requires a moral compass rooted in the Western tradition.
Throughout his tenure at Just Right News, Mason has remained committed to the idea that the future is something to be shaped, not merely accepted. His writing is characterized by a rigorous defense of American exceptionalism and a belief that the country’s best days lie ahead, provided it remains true to its founding ideals. Whether he is investigating the impact of automation on the American workforce or profiling the next generation of aerospace engineers, Mason Reed ensures that his readers are equipped with the insights they need to navigate a changing world with confidence and clarity.