Vercel adds Google's Gemini 4 Argon to AI Gateway with 1M token context
Vercel has made Google's Gemini 4 Argon available on its AI Gateway. According to Vercel, the model is built for coding, agentic work, and complex reasoning, and it offers a 1M token context window.
- Google's Gemini 4 Argon is now available on Vercel's AI Gateway.
- The model has a 1M token context window and accepts text, image, PDF, and video input.
- It uses thinking levels (low, medium, high) instead of thinking budgets.
- The model name is google/gemini-4-argon, usable via the AI SDK, Chat Completions, Responses, and Anthropic Messages APIs.
- Vercel says AI Gateway reflects provider pricing with no markup and no platform fee on inference.
What Gemini 4 Argon offers
Gemini 4 Argon accepts text, image, PDF, and video input and supports tool calling. Vercel says the model has a 1M token context window.
On coding tasks, Vercel says Gemini 4 Argon builds features, fixes bugs, and researches unfamiliar codebases, carrying longer tasks through multiple steps. The model also reads dense diagrams, spreadsheets, layout-heavy documents, and video. Vercel gives the example of a financial analysis spread across several spreadsheet tabs.
Beyond code, the model handles work in finance, health, and law, as well as hard problems in math and science, according to the announcement.
How to call it
Gemini 4 Argon uses thinking levels instead of thinking budgets. The available levels are low, medium, and high. Developers set the level with reasoning in the AI SDK or reasoning_effort in Chat Completions.
The model can be called through the AI SDK, the Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent connected to AI Gateway. The model name to use is google/gemini-4-argon.
Vercel's example uses the AI SDK's streamText function with the reasoning level set to high and the prompt "Write a token bucket rate limiter in TypeScript, with tests."
To use the model in coding agents such as Claude Code, Codex, and Cursor, users install the latest Vercel CLI with npm i -g vercel@latest and run vercel ai-gateway setup. They then select google/gemini-4-argon in the agent. Vercel also points to a coding agents guide and a model playground for trying the model.
About AI Gateway and what it means for developers
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations. Vercel says these are aimed at higher-than-provider uptime. The service includes:
- built-in custom reporting
- Zero Data Retention support
- budgets for API keys
- routing rules
On pricing, Vercel states that AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. The announcement does not give prices for the model itself.
For developers already routing requests through AI Gateway, the addition means Gemini 4 Argon can be reached with the same APIs and tooling they use for other models, including from coding agents. Switching the model name and choosing a thinking level are the main steps described in the source.
Vercel: Gemini 4 Argon now available on AI Gateway
