Google says in the Gemini API changelog that Genie 4 (models/genie-4) became generally available on the Interactions API (v1beta) on November 19. It generates a steerable 16:9 world at 24 fps with synchronized 48 kHz stereo audio in real time, streamed over WebRTC or WebSockets. Worlds can be seeded from text, a 16:9 reference image or both, then steered with WASD or arrow keys and mid-session text events. It is paid tier only, with video output at $17.50 per million tokens, about $0.10 per second. A day earlier Genie 4 opened to Google AI Ultra subscribers in Project Genie.
Key Takeaways
- ✓Official: the November 19 Gemini API changelog entry marks Genie 4 GA, with model ID models/genie-4 on the Interactions API v1beta
- ✓Output: real-time 16:9 video at 24 fps plus 48 kHz stereo audio; keyboard moves take effect in about 0.2 to 0.5 seconds, text events in about 1 to 2 seconds
- ✓Pricing: paid tier only; $1.50 per million input tokens, $9.00 per million text output tokens and $17.50 per million video output tokens (240 tokens per frame, about $0.10 per second with audio)
- ✓Limits: no free tier; Tier 1/2/3 get 2/5/10 concurrent sessions and 50/250/1,000 requests per day; sessions hard-cap at 120 seconds and are served from US data centers only
- ✓Usage: create the interaction on your server, mint a single-session token, connect from the browser over WebRTC, and always call complete() to stop billing
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
Most video generation models work offline: you write a prompt, wait, and get a fixed clip you cannot steer. World models aim for real-time interaction, generating each frame in response to what the player does. Genie 4 is Google DeepMind's interactive world model. It opened to Google AI Ultra subscribers on November 18, and from November 19 developers can call it through the Gemini API.
How it works
Genie 4 runs on the Interactions API over a live two-way connection. A session has four steps: the server creates the interaction, the browser connects over WebRTC or WebSocket with a single-session token, a world_setup event seeds the world, and keyboard or text events steer it. Keyboard moves take effect in about 0.2 to 0.5 seconds, while text events go through world planning and take about 1 to 2 seconds.
Benchmarks
The docs give no benchmark scores, only specs and limits: 16:9 at 24 fps with 48 kHz stereo audio. Looking away from an object for 8 seconds or more, or turning 360 degrees, can make landmarks shift; visual stability may degrade after 60 to 90 seconds, and sessions hard-cap at 120 seconds. Billing is 240 video tokens per frame, about $0.10 per second.
What developers should do
Try it first in the Google AI Studio Live playground, then integrate with the latest @google/genai or google-genai SDK. Three things to watch: there is no free tier; serving is US only, and round trips above 150 ms noticeably slow steering; closing a tab does not stop generation, so always call complete() to end billing.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.