Google: veo3.1-fast
Veo-3.1-fast-generate-preview is a low-latency, high-speed iteration of the Veo 3.1 video generation family, optimized specifically for rapid iterative workflows. Built on a latent diffusion architecture with a highly distilled "Flash" transformer backbone, it is capable of generating low-resolution, high-frame-rate video previews in under 2 seconds. In 2026, it serves as the "drafting engine" for professional creators, allowing them to verify composition, lighting, and temporal consistency before committing to the heavy compute of the full Veo-Ultra model. It introduces a "Continuous Feedback Loop" feature where users can adjust prompts in real-time and see the preview update almost instantly.
All providers for this model are busy right now
Every upstream provider has hit its rate limit. The model comes back automatically once limits lift, usually within hours. Try again in a little while or switch to another model.
Request this model on DiscordInputs used for the providers' own purposes
At least one provider of this model uses your inputs for its own purposes, for example to train AI models. Do not enter personal data of third parties or sensitive data. You can object to this use at any time in your account settings or via "Manage consents" in the chat.
Read the privacy policy