Para contas sem compra anterior: execuções acima de 2 créditos precisam de recarga.
Novo por aqui?
10 créditos grátis (US$ 0,10) ao se inscrever com Google
Utilizável 24 horas após inscrição, até 5 execuções por dia e no máximo 2 créditos por execução. Outros métodos de login começam sem créditos.
02
Examples
Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.
Prompt
a dog riding a skateboard
Duração: 0:05
Settings
aspect_ratio
16:9
duration
5
Prompts de exemplo
Exemplos do catálogo Railwail. Eles não foram gerados ao vivo nesta página.
Nature Scene
Duração: 0:08
Aerial drone shot slowly rising above a misty old-growth forest at dawn, revealing a winding river cutting through the valley below, golden sunlight breaking through clouds
Cinematic Portrait
Duração: 0:05
Close-up of a woman's face as she opens her eyes and looks into the camera, shallow depth of field, soft golden backlight, hair gently moving in the breeze, cinematic 24fps
03
Sobre Google Veo 2
ResumoA partir de 23 de setembro de 2026
Google Veo 2 é um modelo de Google DeepMind na categoria Geração de vídeos. No Railwail, Google Veo 2 custa US$ 0,60 por segundo de vídeo. Uma execução padrão de 8 segundos custa US$ 4,80. Proporções de aspecto suportadas: 16:9 e 9:16. Durações possíveis: 5, 6, 7 ou 8 s. Versão mais recente: Google Veo 3.1.
Fundo
Sobre Google DeepMind
Fundado em 2010 · London, United Kingdom
Google DeepMind is the merged AI research organisation formed in April 2023 when Google Brain and DeepMind (acquired by Google in 2014) were combined into a single unit led by Demis Hassabis (CEO). DeepMind was founded in 2010 by Hassabis, Shane Legg and Mustafa Suleyman, and is famous for AlphaGo, AlphaFold and the Gemini language-model family. On the video side, DeepMind shipped Imagen Video (2022), Lumiere (2024), Veo (May 2024, Google I/O), Veo 2 (December 2024), Veo 3 with native audio (May 2025) and Veo 3.1 (late 2025). Veo is exposed via Vertex AI, the Gemini API, Google Labs (VideoFX, Whisk) and YouTube's Dream Screen.
Latent video diffusion / Diffusion Transformer hybrid with cascaded super-resolution
Veo 2 is a closed text-to-video and image-to-video model that builds on DeepMind's Imagen and Lumiere research. It uses a spatio-temporal latent diffusion architecture with a transformer-based denoiser conditioned on rich text embeddings from Gemini-family encoders and optional image embeddings. Veo 2 generates clips up to 8 seconds at up to 4K resolution (extended versions reach minutes), with strong understanding of camera language ('dolly', 'aerial', '35mm anamorphic') and real-world physics. DeepMind report substantial gains over Veo 1 on motion realism, prompt adherence and detail. The pipeline combines a base diffusion model with cascaded spatial and temporal super-resolution and an upscaler. Veo 2 was trained on a curated YouTube-and-partner video corpus with synthetic captioning at multiple granularities, and post-trained with reward models for prompt adherence and aesthetic quality.
Parâmetros
Undisclosed
Capacidades
Text-to-video and image-to-video generation
Up to 8-second clips, up to 4K resolution
Rich cinematographic prompt vocabulary (lenses, lighting, camera moves)
Strong real-world physics and object permanence
Available via Vertex AI, Gemini API, VideoFX and YouTube Dream Screen
SynthID watermarking embedded in every frame
Multilingual prompts via Gemini text encoders
Lower hallucination of artefacts than Veo 1
Best for: high-quality marketing, film previs, broadcast inserts, enterprise creative.
Treinamento & licença
Curated mix of licensed video, public web video (including YouTube under Google's terms) and synthetic data, with multi-granularity captioning produced by Gemini vision models. Exact dataset size undisclosed.
Licença: Proprietary commercial licence via Google Cloud / Vertex AI and the Gemini API; commercial usage permitted under Google's generative AI terms; SynthID watermark required on all output.
Testes de segurança: Subject to Google's responsible AI framework with safety filters, public-figure filters, child-safety classifiers and provenance via SynthID; covered by Google's Responsible AI Progress Reports.
Limitações conhecidas
No native audio in Veo 2 (audio first appears in Veo 3)
8-second clip limit per base generation
Closed access with gated waitlist on some surfaces
Strict moderation on people, brands and political content
Limited control over exact frame composition without seed images
curl https://railwail.com/api/v1/videos/generations \
-H "Authorization: Bearer $RAILWAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google-veo-2",
"prompt": "A slow drone shot over a misty pine forest at sunrise"
}'
# Response: {"job_id": "...", "status": "queued", ...}
# Poll until status is completed, failed or cancelled:
curl https://railwail.com/api/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAILWAIL_API_KEY"
import os
import time
import requests
API = "https://railwail.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['RAILWAIL_API_KEY']}"}
job = requests.post(
f"{API}/videos/generations",
headers=headers,
json={
"model": "google-veo-2",
"prompt": "A slow drone shot over a misty pine forest at sunrise",
},
).json()
while True:
status = requests.get(f"{API}/jobs/{job['job_id']}", headers=headers).json()
if status["status"] in ("completed", "failed", "cancelled"):
break
time.sleep(5)
print(status["status"], status.get("output_url"))
const API = "https://railwail.com/api/v1";
const headers = {
Authorization: `Bearer ${process.env.RAILWAIL_API_KEY}`,
"Content-Type": "application/json",
};
const job = await fetch(`${API}/videos/generations`, {
method: "POST",
headers,
body: JSON.stringify({
model: "google-veo-2",
prompt: "A slow drone shot over a misty pine forest at sunrise"
}),
}).then((r) => r.json());
let status;
do {
await new Promise((r) => setTimeout(r, 5000));
status = await fetch(`${API}/jobs/${job.job_id}`, { headers }).then((r) => r.json());
} while (!["completed", "failed", "cancelled"].includes(status.status));
console.log(status.status, status.output_url);
Proprietary commercial licence via Google Cloud / Vertex AI and the Gemini API; commercial usage permitted under Google's generative AI terms; SynthID watermark required on all output.
Entrada do catálogo atualizada
23 de setembro de 2026
Parâmetros de entrada
Entradas e configurações do esquema de entrada do modelo. O exemplo na seção API mostra quais delas a API aceita.
Google Veo 2 é um modelo de Google DeepMind na categoria Geração de vídeos. No Railwail você pode chamá-lo com uma chave de API através da API Railwail.
Quanto custa Google Veo 2 no Railwail?
No Railwail, Google Veo 2 custa US$ 0,60 por segundo de vídeo. Uma execução padrão de 8 segundos custa US$ 4,80. O preço é conhecido antes do início da execução. O uso é pago com créditos pré-pagos; 1 crédito equivale a US$ 0,01.
Quais configurações Google Veo 2 suporta?
De acordo com seu esquema de entrada, Google Veo 2 conhece estes parâmetros: prompt, duration (5, 6, 7 ou 8), start_image e aspect_ratio (16:9 ou 9:16).
Qual é a velocidade de Google Veo 2?
Ainda não há execuções medidas suficientes de Google Veo 2 no Railwail para indicar um tempo de execução. Depende da entrada, das configurações e da carga no provedor.
Google Veo 2 é melhor que Google Veo 3.1?
Depende da tarefa. Google Veo 2 (Google DeepMind) e Google Veo 3.1 (Google DeepMind) são ambos modelos na categoria Geração de vídeos. A página de comparação mostra seus preços e especificações lado a lado.
Crie uma chave de API Railwail e envie sua solicitação com o ID do modelo google-veo-2. Exemplos de código para curl, Python e JavaScript estão na seção API desta página.
Kuaishou's Kling v2.1, generating 5 and 10 second videos at 720p or 1080p from text or an image. Known for cinematic camera work and realistic physical motion, available on Replicate via the official KwaiVGI account.
