Skip to content

We're gradually introducing multi-token streaming across our models

UpdateUnverifiedAdded Sep 24, 2026

We're gradually introducing multi-token streaming across our models. Instead of sending tokens individually, we'll now deliver them in batches through 200 evenly-spaced events per second. This change eliminates the artificial delays that occurred with single-token streaming.

Topics: Streaming

Cerebras's release notes

More Cerebras Inference releases

Every Cerebras Inference release

Also shipped on Oct 6, 2025

Cerebras in October 2025

Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.

New releases by email

Tuesday mornings: the week's data, AI and developer-tools releases, only in weeks when something shipped.

Double opt-in. Unsubscribe any time.