Batch Inference 2.0 private beta
Company: Nebius
The claim, verbatim
Batch Inference 2.0 is in private beta for selected customers, running asynchronous inference on dedicated capacity that scales to zero between jobs.
Source (primary)
What was new in Q3 - Nebius (-, news_article)
View cached copy (2026-10-02)Live source ↗Archive.org ↗
Quote: “Batch Inference 2.0 (in private beta for selected customers) runs asynchronous inference on dedicated batch capacity that scales to zero between jobs.”
How we checked this
Checked on October 3, 2026. The cited source supports every part of this claim.
The release notes describe Batch Inference 2.0 in these terms.
Confirmed in the source:
- Batch Inference 2.0 is in private beta for selected customers
- It runs asynchronous inference on dedicated batch capacity
- The capacity scales to zero between jobs
What we did: Read our cached copy of the publisher (https://nebius.com/release-notes/posts/q3-2026) in full (13,073 characters, retrieved October 2, 2026) and checked each assertion in the claim against it.
Additional evidence
confirms What was new in Q3 - Nebius
Quote: “Batch Inference 2.0 (in private beta for selected customers) runs asynchronous inference on dedicated batch capacity that scales to zero between jobs.”