Gemini 4 Argon now available on AI Gateway

Google's Gemini 4 Argon is now available on Vercel's AI Gateway, the company announced, offering a 1M token context window with text, image, PDF, and video input plus tool calling. The model uses thinking levels (low, medium, high) instead of thinking budgets, set via `reasoning` in the AI SDK or `reasoning_effort` in Chat Completions, and is callable through the AI SDK, Chat Completions, Responses, and Anthropic Messages APIs under the model name `google/gemini-4-argon`. AI Gateway reflects provider pricing with no markup and charges no platform fee on inference, including BYOK requests.

Gemini 4 Argon https://vercel.com/ai-gateway/models/gemini-4-argon from Google https://vercel.com/ai-gateway/models/providers/google is now available on AI Gateway https://vercel.com/ai-gateway . Gemini 4 Argon is built for coding, agentic work, and complex reasoning. It has a 1M token context window, accepts text, image, PDF, and video input, and supports tool calling. On coding tasks, 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, which suits tasks like a financial analysis spread across several spreadsheet tabs. Beyond code, it handles work in finance, health, and law, and hard problems in math and science. Gemini 4 Argon uses thinking levels low , medium , and high instead of thinking budgets. Call Gemini 4 Argon through the AI SDK https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk , the Chat Completions https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions , Responses https://vercel.com/docs/ai-gateway/sdks-and-apis/responses , and Anthropic Messages https://vercel.com/docs/ai-gateway/sdks-and-apis/anthropic-messages-api APIs, or a coding agent https://vercel.com/docs/ai-gateway/coding-agents connected to AI Gateway. Set the thinking level with reasoning in the AI SDK or reasoning effort in Chat Completions, and see reasoning https://vercel.com/docs/ai-gateway/models-and-providers/reasoning for the other controls. Use google/gemini-4-argon as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select google/gemini-4-argon in the agent. See the coding agents guide https://vercel.com/docs/ai-gateway/coding-agents for details. Try Gemini 4 Argon in the model playground https://vercel.com/ai-gateway/models/gemini-4-argon . AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting https://vercel.com/changelog/custom-reporting-ai-gateway , Zero Data Retention support https://vercel.com/blog/zdr-on-ai-gateway , budgets for API keys https://vercel.com/docs/ai-gateway/authentication-and-byok/api-keys , routing rules https://vercel.com/docs/ai-gateway/models-and-providers/routing-rules , and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key https://vercel.com/docs/ai-gateway/authentication-and-byok/byok BYOK requests. You can view all language models https://vercel.com/ai-gateway/models?type=text available on AI Gateway.