# Together AI — Canary rollouts: upgrade models in production without downtime

- Company: Together AI (together.ai)
- Announced: 2026-09-22
- Category: developer-tool-release
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.together.ai/blog/canary-rollouts-upgrade-models-in-production-without-downtime
- Record: https://forck.live/items/13150-canary-rollouts-upgrade-models-in-production-without-downtime
- Subject: Inference platform
- Models affected: Qwen2.5-7B, Qwen3.5-9B

Together AI released canary rollouts, a feature for upgrading models in production without downtime. The system uses staged traffic ramps, metric gates, and automatic rollback on dedicated inference, allowing operators to migrate traffic between two deployments with health checks and optional performance gates at each step.

## Evidence

Verbatim from https://www.together.ai/blog/canary-rollouts-upgrade-models-in-production-without-downtime:

> Rollouts move live traffic from your current model to a new checkpoint in gated steps. Health checks always run before traffic moves; on a canary you can also add metric gates (say p95 latency or error rate) that run after each step.

---

Record: https://forck.live/items/13150-canary-rollouts-upgrade-models-in-production-without-downtime
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
