genie-4 · Google
Genie 4 is Google’s latest real-time interactive world generation model. Through the Interactions API, it can stream controllable video at 24 frames per second in a 16:9 aspect ratio, while simultaneously outputting 48 kHz stereo audio.
Genie 4 is Google’s latest real-time interactive world generation model. Through the Interactions API, it can stream controllable video at 24 frames per second in a 16:9 aspect ratio, while simultaneously outputting 48 kHz stereo audio.
On AIHubMix, Genie 4 costs $1.5 per million input tokens and $9 per million output tokens.
Genie 4 accepts text, image, audio and video input. It returns video output.
Genie 4 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to genie-4 — no other code changes needed.
Genie 4 is developed by Google. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Genie 4 was released on November 20, 2026 by Google.
Gemini 4 Neon is the latest model in Google’s Gemini 4 series. It features frontier-level…
Gemini 4 Hydrogen is a Google Gemini 4 model focused on speed and efficiency. Potential…
Gemini Decision 1 is designed for judgment and decision-making tasks, helping developers…
Gemini 3.8 Live is a multimodal AI model from Google that delivers a low-latency…
Gemini 2.5 Flash Live is Google's multimodal AI model for real-time interactions…
Gemini 4 Carbon is Google DeepMind’s multimodal model for complex coding, long-running…
Use Genie 4 via the AIHubMix unified API — one interface for every major LLM.