Gemini 4 Argon now available on AI Gateway
Vercel’s AI Gateway now supports Google’s Gemini 4 Argon model, expanding coding, agentic, and reasoning capabilities with a 1M token context window and multi-modal input support.
Gemini 4 Argon from Google has been added to Vercel’s AI Gateway, enabling developers to integrate the model directly into their workflows. The model is designed for coding tasks, agentic workflows, and complex reasoning, with a context window of 1 million tokens. It accepts text, images, PDFs, and video as input, and supports tool calling for extended task execution. This makes it suitable for multi-step processes such as building features, debugging, or analyzing unfamiliar codebases.
Beyond coding, Gemini 4 Argon is capable of handling tasks in finance, health, and law, as well as solving advanced problems in math and science. The model introduces thinking levels—low, medium, and high—instead of traditional thinking budgets, allowing users to adjust reasoning depth. Developers can access it through the AI SDK, Chat Completions, Responses, and Anthropic Messages APIs, or via coding agents connected to AI Gateway.
To use Gemini 4 Argon with coding agents like Claude Code, Codex, or Cursor, users must install the latest Vercel CLI and run a setup command. The agent selection process includes choosing google/gemini-4-argon, with additional guidance available in Vercel’s coding agents guide. This integration streamlines the deployment of AI-powered coding assistants across multiple platforms.
AI Gateway provides a unified interface for calling models, tracking usage and costs, and configuring retries, failover, and performance optimizations to improve uptime. The service includes features such as custom reporting, Zero Data Retention support, API key budgets, and routing rules. Pricing aligns with provider rates, with no platform fees on inference, including Bring Your Own Key requests. A full list of supported language models is available on AI Gateway.