active_sessions autoscaling metric for TTS
UpdateUnverifiedAdded Sep 24, 2026
Dedicated endpoint autoscaling now accepts active_sessions , which targets concurrent open client WebSocket sessions per replica on a TTS deployment ( AVERAGE_VALUE only). The default inflight_requests metric also covers TTS handlers, so HTTP TTS traffic can keep scaling without a policy change. See Configure autoscaling .
Topics: Governance
More Together AI platform releases
Every Together AI platform release| Date | Release | Type |
|---|---|---|
| Aug 28 | New serverless modelsunverified Update | Update |
| Aug 31 | New serverless modelsunverified Update | Update |
| Aug 27 | Billing usage API (beta)unverified Beta | Beta |
| Aug 27 | File upload progress in the CLI and Python SDKunverified Update | Update |
| Aug 27 | Slurm cluster kubeconfig for project membersunverified Update | Update |
| Aug 27 | Legacy API key regenerationunverified Update | Update |
| Aug 27 | Model deprecationsunverified Deprecation | Deprecation |
| Sep 1 | Pricing updateunverified Pricing | Pricing |
Also shipped on Aug 29, 2026
Together AI in August 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.