Preemptible compute for GPU clusters
PreviewUnverifiedAdded Sep 24, 2026
Preemptible compute is now in public preview for Kubernetes GPU clusters. Alongside standard nodes, you can set a preemptible GPU target, and Together provisions toward it as spare capacity becomes available, at a flat discounted rate relative to on-demand.
Topics: Developer tools
More Together AI platform releases
Every Together AI platform release| Date | Release | Type |
|---|---|---|
| Sep 10 | What's new:unverified Update | Update |
| Sep 10 | Together CLI v2.33.2unverified Beta | Beta |
| Sep 11 | New serverless modelsunverified Update | Update |
| Sep 8 | New models available for fine-tuningunverified Update | Update |
| Sep 14 | New serverless modelsunverified Update | Update |
| Sep 15 | Rollouts for dedicated model inferenceunverified Beta | Beta |
| Sep 15 | Together CLI v2.34.0unverified Beta | Beta |
| Sep 15 | Model deprecationsunverified Deprecation | Deprecation |
Also shipped on Sep 10, 2026
Together AI in September 2026
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.