Model Releases
New on Dedicated Model Inference: canary rollouts. Upgrade the model behind a live endpoint without downtime. Traffic moves from your curren…
New on Dedicated Model Inference: canary rollouts. Upgrade the model behind a live endpoint without downtime. Traffic moves from your current deployment to the new checkpoint in gated steps (default 5
New on Dedicated Model Inference: canary rollouts. Upgrade the model behind a live endpoint without downtime. Traffic moves from your current deployment to the new checkpoint in gated steps (default 5% → 25% → 50% → 100%). Health checks run before any traffic shifts. After every step, metric gates compare the new model's p95 latency and error rate against the old one. If a gate trips, the rollout pauses at the canary share and waits for you: resume, promote to 100%, or roll back. Three strategies: canary, blue-green, and rolling. Available now via the tg CLI, REST API, and Python SDK. Learn how to start a rollout: https://www.together.ai/blog/canary-rollouts-upgrade-models-in-production-without-downtime
Related
- PSA: Just added a few thousand chips, including B200s and B300s to our Dedicated Model Inference (http://api.together.ai/endpoints). With De…
- Nemotron 3.5 Lightning is available on Together AI through Dedicated Model Inference, giving teams reserved capacity and predictable perform…
- for september, we’re cutting the price of Dedicated Inference on H100s from 5.49/hr to 3.99/hr new + existing deployments get the lower pr…
Source: Together AI (X) | 2026-09-22