VideoGenReview

What each AI video model's release notes say changed

Batch and async requests for AI video models

Batch APIs accept many generation requests at once and return results later; async endpoints return a job to check on instead of waiting for the video. From 3 source pages, read 2026-09-25; no maker pays to be listed.

Video generation takes long enough that waiting on one open request is awkward. xAI's Batch API took video jobs from March 2026, and OpenAI's Sora API added Batch API support the same month. LTX made async versions of all its video generation endpoints in May 2026, in beta.

These notes change nothing about the pictures. They change how a developer queues work, which is why the register files them under access.

For a studio making many clips at once, a batch route is often the difference between a script that runs overnight and one that needs a person watching it. xAI's note adds that video URLs in batch results expire after an hour, a detail that decides how quickly results have to be collected.

Where the term appearsOne dot per dated entry.Where the term appears2026-03-12Sora, Sora 22026-03-15Grok Imagine, Not named in the note2026-05-03LTX, Not named in the note
Fig. 1 One dot per dated entry.
Entries that show the term, oldest first, read 2026-09-25.
DateLineVersionWhat changed
12 March 2026SoraSora 2Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs
15 March 2026Grok ImagineNot named in the noteThe Batch API accepts video generation jobs
3 May 2026LTXNot named in the noteAsync versions of every video generation endpoint, in beta

Inclusion rule. Entries whose note uses or shows the term. Order. By date, oldest first; undated rows last.

1In the notes

Expanded the Sora API with reusable character references, longer generations up to 20 seconds, 1080p output for sora-2-pro , video extensions, and Batch API support for POST /v1/videos .

OpenAI, API changelog

The Batch API now supports image generation, image editing, and video generation in addition to chat completions.

xAI, API release notes

Async API expanded to all video generation endpoints (Beta)

LTX, API changelog
  • March 12
    Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs2026OpenAI, API changelog / since 2026-03-12 / checked 2026-09-25
  • Mar 15
    The Batch API accepts video generation jobsxAI, API release notes / since 2026-03-15 / checked 2026-09-25
  • Async API
    Async versions of every video generation endpoint, in betaLTX, API changelog / since 2026-05-03 / checked 2026-09-25

2Using the models, not reading about them

Release notes such as “Batch and async” matter once a pipeline runs the models; SceneMixer's guides describe how it does:

480P is the default and is genuinely fine on a phone; 720P is the usual upgrade when the series is working.

SceneMixer, Vertical AI Video Generator — “What resolution should I publish at?” (read 2026-10-13)

Doubao Seed 2.1 Pro is the family’s full-size tier at 100% of the base text rate, twice the default. Same three jobs — reading, writing, storyboards — with more headroom on long, crowded episodes: it holds the storyboard’s strict format more reliably and keeps track of many characters and locations in one pass.

SceneMixer, Doubao Seed 2.1 Pro (read 2026-10-13)

3Other terms

4Notes read