Hosted inference rollout is invite-first. Abuse-resistant keys, egress controls, and model allowlists ship with enterprise workspaces.

Vocifer AI
Docs
Getting started

Getting started

Base URLs, the /v1 prefix, and how to think about environments for Vocifer AI inference.

All public routes in this guide sit under the /v1 prefix (for example /v1/models, /v1/chat/completions).

Base URL

EnvironmentExample base
Productionhttps://inf.vocifer.com/v1
Staging / previewIssued per workspace in onboarding

Replace the host with the one in your dashboard or contract. Every example below uses https://inf.vocifer.com/v1 unless noted otherwise.

TLS and versioning

  • Use HTTPS in production.
  • Breaking HTTP changes will be versioned (e.g. a future /v2); /v1 stays stable for the life of your integration unless we publish a migration window.

Next: Authentication — send your first authorized request.

OverviewAuthentication