Run locally
Validate the local path on your own hardware before you commit to rollout policy.
Open local setupOctomil gives teams one place to route requests, roll out safely by cohort, manage cloud fallback, and review fleet behavior as traffic moves into production.
import com.octomil.sdk.Octomil
val client = Octomil(publishableKey = "oct_p12....")
client.initialize()
val response = client.responses.create(
model = "gemma-3-1b",
input = "What's the capital of Canada?"
)
println(response.outputText) > The capital of Canada is Ottawa. Use the route that matches where your team is today.
Validate the local path on your own hardware before you commit to rollout policy.
Open local setupSee the difference between a framework and a production control plane.
Read the comparisonModel what happens when routine traffic stays on-device instead of going to cloud.
Open calculatorOctomil makes the execution policy legible, so teams can inspect runtime preference, device targeting, rollout state, and fallback rules in one place.
Example policy fields for a routine mobile cohort.
Package once, release by cohort, and keep the production path legible.
One packaging path across CoreML, LiteRT, MLX, ONNX, and browser runtimes.
Roll out by cohort, hold changes, and roll back without rebuilding the model path.
Keep routine inference local and use cloud only when hardware or quality requires it.
When procurement, privacy, or security requirements show up, the platform should still feel manageable.
Support for SSO, SCIM, scoped access, and audit history.
VPC and privacy-sensitive deployment options when review requirements show up.
Security materials, deployment planning, and rollout review support.
We can walk through the model and runtime choices, rollout plan, and fallback policy with your actual workload.