
Genie 4 en la API de Gemini: $0.10 por segundo, facturado hasta que cuelgues
- OrcaNUEVOOrcaCyber: Hy4 Flash Abliterated / Uncensored2026-11-18$0.07 / $0.28 por 1M de tokens · 187 tok/s
- tencentNUEVOTencent: Hy4 Flash2026-11-16$0.02 / $0.07 por 1M de tokens · 413 tok/s
- GoogleNUEVOGoogle: Gemini 4 Carbon2026-11-10$2.00 / $10.00 por 1M de tokens · 87 tok/s
- AnthropicNUEVOAnthropic: Claude Fable 5.22026-11-09$8.00 / $40.00 por 1M de tokens · 119 tok/s
- orcaNUEVOOrca: OrcaC2 1.02026-11-079 tok/s
- OrcaOrcaCyber: GLM 5.3 Abliterated / Uncensored2026-11-04$3.00 / $5.00 por 1M de tokens · 89 tok/s
- OrcaOrcaCyber: Hy4 Abliterated / Uncensored2026-11-04$0.80 / $1.60 por 1M de tokens · 135 tok/s
- OrcaOrcaCyber: Kimi K3.1 Pro Abliterated / Uncensored2026-11-04$2.00 / $5.00 por 1M de tokens · 78 tok/s
- tencentTencent: Hy42026-11-04$0.83 / $2.50 por 1M de tokens · 116 tok/s
- OrcaOrcaCyber: MiniMax M3.1 Flash Abliterated / Uncensored2026-10-29$0.80 / $1.60 por 1M de tokens · 114 tok/s
- OrcaOrcaCyber: GLM 5.3 Flash Abliterated / Uncensored2026-10-27$0.80 / $1.60 por 1M de tokens · 66 tok/s
- OrcaOrcaCyber: Qwen3.8 Flash Next Abliterated / Uncensored2026-10-26$0.80 / $1.60 por 1M de tokens · 91 tok/s
- OrcaOrcaCyber: MiMo V2.6 Flash Abliterated / Uncensored2026-10-26$0.80 / $1.60 por 1M de tokens · 41 tok/s
- MoonshotMoonshotAI: Kimi K3.1 Pro2026-10-2447Inteligencia
- OrcaOrcaCyber: DeepSeek V4.1 Flash Abliterated / Uncensored2026-10-23$0.80 / $1.60 por 1M de tokens · 212 tok/s
- minimaxMiniMax: M3.1 Flash2026-10-1929Inteligencia
- OrcaOrca: OrcaCyber Ultra 1.02026-10-17$5.00 / $10.00 por 1M de tokens · 111 tok/s
- deepseekDeepSeek: DeepSeek V4.1 Flash 10172026-10-1733Inteligencia
- DeepSeekDeepSeek: DeepSeek V4.1 Flash 09102026-10-17$0.15 / $0.60 por 1M de tokens · 168 tok/s
- DeepSeekDeepSeek: DeepSeek V4.1 Flash2026-10-1740Inteligencia
The detail that decides whether Genie 4 is a toy or a line item is not the 720p picture. It is that Google bills the model by the second of streamed output and keeps billing until your code tells it to stop. Genie 4 reached the Gemini API on November 19, 2026, one day after it went live inside Project Genie for Google AI Ultra subscribers, and on the same day Project Genie invitations started reaching Google AI Pro members who had joined the waitlist. That pricing model — roughly $0.10 per second, no free tier, no caching, no batch discounts — is the part worth reading carefully before anyone puts a world model behind a product surface. The comparison everyone will make is against Gemini Omni 1.2 Flash, Google's offline video model at about $0.07 per second of 720p; the two look close on a rate card and behave nothing alike in a build.
Tres fechas, y solo una de ellas es el lanzamiento
Genie 4 has been announced three times in three weeks, which is why the coverage of it keeps talking past itself. Google DeepMind published the research announcement on October 27, 2026, with access limited to trusted testers and a public waitlist. On November 18 it began rolling the model out inside Project Genie to eligible Google AI Ultra subscribers, alongside upgrades to Genie 3 and a community gallery. On November 19 it opened the door developers actually care about: models/genie-4 on the Gemini API, through the Interactions API and Google AI Studio.
The fourth event is the one in the signal: on the evening of November 19, TestingCatalog posted a screenshot of an invitation telling a Google AI Pro member they were off the Project Genie waitlist and now had access "as part of your Google AI Pro subscription." That is a user report, not a Google announcement, and at the time of writing the Project Genie page still reads "available at launch for eligible Google AI Ultra subscribers. Google AI Pro members can join the waitlist." But waitlist invitations going out in volume is how a staged rollout widens, and it is the difference between a $99.99 subscription and a $19.99 one for the consumer half of this product.
What none of those four events changed: the model. Same weights, same session cap, same limitations Google published in October and again in the November model card.
El precio real de un mundo, por segundo
Genie 4 is priced as video tokens rather than as a request. Google's rate card lists $1.50 per million input tokens for text and reference images, $9.00 per million output text tokens, and $17.50 per million output video tokens with the 48 kHz stereo audio bundled in. Because the model emits 240 video tokens per frame at 24 frames per second — 5,760 tokens a second — that works out to roughly $0.10 per second of streamed world, or about $6.05 a minute. These are Google's published numbers, not an independent measurement; nobody outside Google has published a metered bill to check them against.
The arithmetic that matters is what a session can cost. Google caps a session at 120 seconds, and says visual coherence and object permanence are strongest during the first 45 to 90 seconds. So the useful part of a session is $4.50 to $9.00, and the ceiling on one uninterrupted session is about $12.00. That is cheap for a pre-visualization pass and expensive for anything that runs while a user is idle.
The billing mechanics are where a prototype turns into an incident. Google's own documentation warns that exiting a local block or closing a browser tab detaches the transport without stopping server-side generation. The only things that stop the meter are complete() or cancel(); detachment does not, and Genie 4 has no session resumption, so a dropped socket cannot be resumed and still costs you until the session ends. Google's prompt guide notes that AI Studio itself pauses a stream when the tab is hidden for more than 10 seconds, precisely so idle tabs do not burn paid video tokens. Your client has to do that job yourself.

Cómo se ve realmente llamarlo
Genie 4 is not a generateContent model and it is not on the Live API. It runs on the Interactions API, which Google has described as generally available since June 2026 and as the place new models and capabilities launch. The endpoint accepts models/genie-4 or the bare genie-4, requires api_version v1beta, and requires a paid-tier API key — the free tier is listed as not available.
El modelo de conexión es la parte inusual, y determina lo que puedes construir:
• Transporte — WebRTC para navegadores (elemento de vídeo más un canal de datos SCTP para eventos de control JSON) o WebSocket para Python y Node, que entrega tramas JPEG en base64 y PCM estéreo de 16 bits a 48 kHz que decodificas tú mismo.
• Tokens de sesión — el servidor crea una interacción, acuña un token de autenticación de sesión única, y solo ese token llega al cliente. La clave de API nunca llega al navegador, que es la única pieza de este diseño que es sencillamente buena.
• Eventos — un world_setup evento inicializa el mundo a partir de texto, una imagen de referencia de 16:9 de menos de 48 KB en WebRTC, o ambos; user_action transporta key_down/key_up nativos para WASD y las cuatro teclas de flecha; los eventos input de mitad de sesión transportan texto que cambia el clima, los objetos o los eventos mientras el flujo se ejecuta.
• Startup cost — first frame arrives roughly 5 to 9 seconds after the world prompt, per Google's integration guide. That is dead air you pay for only insofar as tokens are emitted, but it is dead air a user stares at.
• Steering latency — about 0.2 to 0.5 seconds of visual response at low network round-trip time. Google serves the model from the United States, Western Europe and Japan, and says higher latency outside those regions delays steering and can reduce frame rate. A product aimed at users in, say, Brazil or India is not running this at the frame rate the demos show.

Los límites que determinan si se lanza
Los límites de velocidad se expresan en sesiones concurrentes, no en solicitudes, que es la unidad correcta para un modelo en streaming y una unidad incómoda para la planificación de capacidad. En el nivel 1 de la API tienes dos sesiones activas concurrentes y 50 solicitudes al día; el nivel 2 ofrece cinco y 250; el nivel 3 ofrece diez y 1000. Los mensajes de control dentro de la sesión no consumen cuota adicional. Dos mundos simultáneos es un presupuesto de demostración, no un presupuesto de lanzamiento.
Las brechas de capacidades son igual de trascendentales, porque son las que un arquitecto descubre tarde:
• Sin llamada a funciones, sin salidas estructuradas, sin ejecución de código y sin almacenamiento en caché de contexto en Genie 4. El razonamiento tiene que ocurrir en un modelo diferente y enviarse como texto.
• Sin Batch API, sin Flex inference y sin Priority inference. No puedes sacrificar latencia por coste, ni puedes pagar por adelantarte en una cola.
• Safety filters are session-fatal, not request-fatal. Google's prompt guide says real human faces, public figures and recognizable brand IP can block a world_setup or close an active session mid-run — which, given the billing model, means a blocked session is a session you were paying for.
• Roughly a minute of usable coherence. Two minutes is the cap, 45 to 90 seconds is the honest working range, and Google lists camera latency, intricate physical interactions, audio precision and long-term scene permanence as open problems.
Genie 4 or Gemini Omni 1.2 Flash?
Both are video models with native audio on the same API key, and they answer different questions. Gemini Omni 1.2 Flash generates and edits fixed clips of up to 15 seconds, is generally available on the paid tier, charges $12.00 per million video tokens — about $0.07 per second at 720p, $0.023 at 360p, $0.104 at 1080p with upsampling, $0.209 at 4K — and can be batched, edited and upsampled offline. Genie 4 generates a world you steer in real time and cannot be scheduled, batched or cached at all.
• Interactivo frente a fijo — Genie 4 responde a teclas e indicaciones durante la sesión; Omni genera un clip que luego editas.
Costo por segundo: alrededor de $0.10 para Genie 4 frente a unos $0.07 para Omni a 720p, antes de la opción más económica de Omni a 360p y de la inevitable sobrecarga de sesión de Genie.
• Límite superior — 120 segundos de transmisión en vivo frente a 15 segundos de clip, pero el clip puede alcanzar 4K y la transmisión llega como máximo a 720p.
• Transporte — una sesión persistente de WebRTC o WebSocket frente a una solicitud ordinaria.
• Carga operativa: Genie 4 requiere gestión del ciclo de vida de las sesiones y un interruptor de corte de facturación; Omni no requiere ninguno de los dos.
Si el resultado es una toma, usa Omni. Si el resultado es alguien caminando dentro de ella, paga los tres centavos adicionales por segundo y acepta la carga operativa.
Lo que realmente cambia la lista de espera de Pro
For a developer, nothing measurable. The Gemini API path to Genie 4 is gated by billing tier, not by subscription, and a Google AI Pro membership does not come with an API key that unlocks it. What the invitations in the signal change is the consumer side: Project Genie is drifting from a $99.99 Google AI Ultra feature toward something the $19.99 Google AI Pro tier can reach, which is roughly how Google has widened access to every Gemini-adjacent product it has shipped. If invitations are going out now, the reasonable planning assumption is broader Pro access in weeks, not quarters — but assume it, do not quote it, because Google has not published a date and the waitlist page still reads as a waitlist.
Si ya pagas por AI Ultra, la API tiene una facturación aparte y una clave aparte. Nada del descuento de la suscripción se traslada.
Dónde encaja un router en un stack de streaming
Genie 4 is not on OrcaRouter and there is no honest way to pretend a stateful, per-second video stream is a chat completion. The reasoning half of a Genie pipeline is a different matter: the prompt construction, the event planning, the safety pre-checks and the post-session analysis are ordinary model calls, and Gemini 4 Argon at $2.00 / $10.00 per million tokens and Gemini 3.8 Flash at $0.75 / $3.75 per million are both live on our catalogue through one OpenAI-compatible key. That is one contract and one bill for the text side while the video side stays on Google's meter, and the 0% markup means a Google price change on those models lands on our side the same day rather than whenever a reseller reprices.
La conmutación por error automática importa más aquí que en una carga de trabajo de chat normal, porque una sesión de Genie no se puede reintentar de forma barata: si falla la llamada de planificación que genera un prompt del mundo, habrás desperdiciado la latencia de configuración y, en el peor de los casos, parte de una sesión de pago. Enrutar esa llamada entre proveedores es el seguro barato.

¿Quién debería gastar el dinero esta semana?
Construye el prototipo si lo que estás probando es si un mundo interactivo cambia el comportamiento de un usuario: una revisión de diseño espacial, un entorno de entrenamiento de agentes, una pasada de previsualización en la que un director quiere recorrer el set. Por 12 dólares por una sesión de dos minutos, puedes realizar cincuenta sesiones por el precio de un día del tiempo de un contratista, y el techo de 720p no es la restricción en esa decisión.
Wait if the thing you are testing is cost per output minute for finished video. Genie 4 is more expensive per second than Gemini Omni 1.2 Flash, capped at 720p, and offers no batch or priority path; the world model's advantage is that a human is inside it, and that advantage evaporates the moment your pipeline is unattended. Wait too if your users are outside the three serving regions, because the frame rate you demo in California is not the frame rate a user in São Paulo sees.
The open question worth watching is whether Google publishes an idle or paused-session rate. Right now the meter runs on streamed output until completion is called, which makes every Genie 4 integration a small exercise in billing discipline. A pause primitive, or a cheaper low-motion mode, would change the economics of this model more than any quality improvement in the next release.
