Video generation just became one sdk call. grok imagine, on vercel's ai gateway by september 22,…
video generation just became one sdk call. grok imagine, on vercel's ai gateway by september 22, turns the experimental_generatevideo function into a route that polls until the clip is ready.
the video api stopped being a separate project.
Context
xAI's video generation documentation says the SDK handles asynchronous polling automatically, and describes a raw REST flow that starts a request and polls a status that can be done or expired, with configurable duration, aspect ratio and resolution and native 1080p on grok-imagine-video-1.5. Vercel's model page says Grok Imagine Video was released January 28, 2026 and is available through Vercel AI Gateway, with text to video, image to video and video editing modes, and that Zero Data Retention is not available for the model. A Vercel changelog published August 25, 2026 says AI Gateway now supports asynchronous video generation.
On the Vercel side, generateVideo by default keeps one HTTP request open until the result is ready, and the August 25 changelog adds asynchronous options, webhook, polling and retrieve later, through experimental_startVideo and experimental_getVideoStatus. So one SDK call that waits describes the default behavior and not a new September 22 launch. The note names experimental_generatevideo, and the changelog text read uses generateVideo for the default call, so the exact function name is not confirmed. Snippets list availability of Grok Imagine on the gateway on February 19, 2026 and of version 1.5 on June 3, 2026, which is compatible with by September 22 and does not contradict it, while the exact SDK function and polling behavior at that cutoff are unverified. No per-clip price was read. The AI SDK page marks video generation as experimental. The video api stopped being a separate project is the author's take.
Watch next
- A dated first-party September 22 item and per-clip pricing.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 23 September 2026 at 01:04 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →