Nano Banana 2.1 is now available on Replicate
Nano Banana 2.1 has launched on Replicate, expanding model access to the platform and supporting integrations with agent workflow skills.
#model-deployment
View all AI newsTogether AI adds canary rollouts to Dedicated Model Inference
Dedicated Model Inference can now upgrade the model behind a live endpoint without downtime. Traffic shifts in gated steps, and metric gates can pause a rollout if p95 latency or the error rate worsens.