AI modelPremium plan

Gemini 4 Carbon

Google's deep-reasoning Gemini 4 model via the Vercel AI Gateway on Vertex AI, with web search, image input and a 1M-token context window. It thinks for longer, so replies can take noticeably more time. Uses 2 premium requests per send before length multipliers. Supports image input. Supports web search.

The model you pick is the model that answers. Some replies follow our crisis protocol and may be fixed text.

Specifications

IntelligenceHigh
SpeedSlow
Context window1,000,000 tokens
Knowledge cutoffNot officially published
Input price$2.00 / 1M tokens
Output price$10.00 / 1M tokens
Request cost2 premium requests
Plan tierPremium
InputText, Image
OutputText
FeaturesCached input: $0.10 / 1M tokens, 2 premium requests per send before length multipliers, Function calling supported, Web search supported, Served through the Vercel AI Gateway (google/gemini-4-carbon), Zero data retention and no prompt training
Model IDgemini-4-carbon

Specifications and list prices are as published by the model's provider and can change. Request cost is what the model uses on just4o.chat.

Related models