Key Info

LiteLLM has added support for Gemini 4 Argon, Google's flagship reasoning model, which is officially rolling out today. Launch pricing is available until November 30.

Highlights

  • Input: $2.00 per million tokens
  • Output: $10.00 per million tokens
  • Cache read: $0.10 per million tokens
  • Launch pricing valid until November 30
  • Pricing and limits details available via the provided link