Skip to content

Veo 3.1 Fast Generate

Veo 3.1 Fast Generate is the speed-optimized Veo 3.1 model, bringing the 3.1 generation's improvements to a lower-latency serving configuration, designed for rapid prompt iteration, parallel generation batches, and high-frequency creative workflows where each generation feeds the next.

text-to-videoimage-to-video
index.ts
import { experimental_generateVideo as generateVideo } from 'ai';


const result = await generateVideo({
  model: 'google/veo-3.1-fast-generate-001',
  prompt: 'A serene mountain lake at sunrise.'
});
OverviewPlaygroundAboutProvidersThroughputLatencySimilarFAQ
Latency

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.