Google has unveiled Gemini 4 Argon, a new frontier artificial intelligence model designed to tackle complex, long-running tasks in software engineering, enterprise work and cybersecurity, as the company pushes its AI systems toward increasingly autonomous workflows.
In a blog post, the technology giant said Argon is initially being rolled out "to a set of trusted cyber defenders through our Fairwind Program," rather than being released broadly to consumers. Google plans to gradually expand access while testing safeguards and gathering feedback before eventually making the model available to "developers, enterprises, and consumers."
The broader rollout is expected to begin with paid API customers and Google AI Ultra subscribers, although Google has not announced a specific release date. One of the biggest changes is the amount of work Argon can produce during a single trajectory. Google said it has expanded the model's output token limit "to an industry-leading 1M tokens, up from the previous 64K tokens."
The company said thousands of Google employees are already using Argon internally for specialized coding, research, and writing. In one example highlighted by Google, Argon helped "optimize the spacetime resources (qubits × gates) of subroutines that bottleneck important applications. In one example, it beat the published baseline by 40% in a matter of minutes."
Google also said a group of Argon agents analyzed "profiling telemetry to autonomously identify and apply memory optimizations across Google's data centers, freeing up over 300 TiB of memory once rolled out, with an estimated 500 TiB to 1 PiB in total savings."
Argon is also being put to work on an ambitious effort to migrate large C and C++ codebases to the Rust programming language. Google stressed that the migrations are subject to "rigorous automated and manual auditing, emulation testing, and review before rolling out to production."
The company said the model scored 77.9% on DeepSWE v1.1, an evaluation of long-horizon software engineering tasks. Argon also ranked first on AutomationBench with a score of 51.3%, according to Google, while reaching 91.7% on LVBench, an evaluation focused on long-video understanding.
Google said Argon can autonomously "find, validate, and patch critical software vulnerabilities." Cybersecurity company Wiz is already using the model through its Scan for Good initiative, which works to identify security risks affecting critical public infrastructure.
According to Google, Argon discovered a "critical vulnerability exposing sensitive personal information across healthcare software used by hospitals worldwide, identifying a severe risk that previous frontier models had missed."
Argon also tied for first place on CWE-bench v1, a vulnerability-remediation benchmark, with a score of 68%, Google said. The company is taking a phased approach partly because those cybersecurity capabilities could potentially be misused.
Google said it is strengthening protections against malicious cyber activity, chemical, biological, radiological and nuclear threats, prompt-injection attacks and AI systems acting beyond a user's intentions.
Trusted cybersecurity defenders and Google's internal teams, however, will receive access to Argon without the standard cyber guardrails so they can use its full defensive capabilities. Google plans to offer Gemini 4 Argon at an introductory price of $2 per million input tokens and $10 per million output tokens. Cached input tokens will receive a 95% discount from the standard input price.
