Artificial intelligence news.
Straight from the original announcements.

Vercel adds xAI's Grok Imagine Video 1.5 Lite to AI Gateway

October 8, 2026Source: Vercel
Vercel adds xAI's Grok Imagine Video 1.5 Lite to AI Gateway
Image: Vercel

Vercel has made Grok Imagine Video 1.5 Lite from xAI available on its AI Gateway. The lightweight model generates video with native audio from text prompts and images.

Key points
  • Grok Imagine Video 1.5 Lite from xAI is now available on Vercel's AI Gateway.
  • The model creates video with native audio from text prompts and images.
  • Clips run from 1 to 15 seconds at 480p, 720p or 1080p, in seven aspect ratios.
  • Developers use the model ID spacexai/grok-imagine-video-1.5-lite in the AI SDK.
  • The model can also be tested in the AI Gateway Playground.

What the model does

According to Vercel, Grok Imagine Video 1.5 Lite is a lightweight model that turns text prompts and images into video with native audio. It produces clips from 1 to 15 seconds long and supports 480p, 720p and 1080p resolutions.

Seven aspect ratios are available, covering widescreen, square and portrait formats. Vercel says this lets developers create horizontal scenes or vertical videos from the same generation workflow.

How to use it in the AI SDK

To start generating videos, developers set the model to spacexai/grok-imagine-video-1.5-lite in the AI SDK. Vercel's example uses the experimental_generateVideo function, imported from the ai package and aliased as generateVideo.

The sample call passes the model name, a prompt ("A paper sailboat drifts on a quiet pond at sunrise."), a resolution of 1920x1080, an aspect ratio of 16:9 and a duration of 10 seconds. The function returns a video object.

Vercel also suggests chaining an image model with Grok Imagine Video 1.5 Lite, so that a still image is created and then animated in one flow.

Playground and gateway features

Users can also try the model directly in the AI Gateway Playground, without writing code first.

AI Gateway is Vercel's service that provides one API for calling models, tracking usage and cost, and configuring routing, retries and failover. Access works with either an AI Gateway API key or a provider key that the developer brings.

What it means for developers

For teams already using AI Gateway, the addition puts a video generation model with native audio behind the same API they use for other models. Because usage and cost tracking, routing, retries and failover are handled by the gateway, video generation can sit in the same workflow as other model calls. The range of durations, resolutions and aspect ratios also means one model can serve both landscape and vertical video needs, according to Vercel's description.

Vercel did not publish pricing or performance figures in the announcement. Further model details are linked from the changelog entry.

Related news

Vercel adds DeepSeek Search and Fetch to AI Gateway
For developersNovember 6, 2026

Vercel adds DeepSeek Search and Fetch to AI Gateway

Vercel has added DeepSeek Search and DeepSeek Fetch to AI Gateway, allowing developers to give models web search and page retrieval tools through one AI Gateway API key.…

Vercel Adds Gemini Omni 1.2 Flash Video Generation to AI Gateway
Products and toolsNovember 5, 2026

Vercel Adds Gemini Omni 1.2 Flash Video Generation to AI Gateway

Vercel has added Google’s Gemini Omni 1.2 Flash to AI Gateway, allowing developers to generate and edit videos through one API key without a separate Google account. The…

Vercel adds 14 ElevenLabs audio models to AI Gateway, at half price for now
Products and toolsOctober 27, 2026

Vercel adds 14 ElevenLabs audio models to AI Gateway, at half price for now

Vercel has partnered with ElevenLabs to bring 14 ElevenLabs models to AI Gateway, covering transcription, speech synthesis, realtime voice agents, music, sound effects…