Gemini 4 Argon

Google's flagship reasoning model.

Context window is unified across input and output. Max output is 65,536 tokens synchronously, or up to 1.05M with long decode. Implicit caching only.

Make your first request

{
  "model": "gemini-4-argon",
  "messages": [
    {
      "role": "user",
      "content": "Hello, world."
    }
  ]
}