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

Vocifer AI
Docs
Models catalog

Models catalog

List available models, context limits, and pricing metadata with GET /v1/models.

GET /v1/models

Returns a machine-readable catalog: model ids, context bounds, pricing as decimal strings per token unit, and advertised features (tools, JSON mode, etc.). Poll this endpoint from CI or your router so cost quotes never drift from what the fleet actually serves.

curl -sS "https://inf.vocifer.com/v1/models" \
  -H "Authorization: Bearer $VOCIFER_API_KEY"

Optional:

X-Vocifer-Organization-Id: <organizationId>

How to use the response

  • Pick a model id for chat/completions.
  • Treat pricing fields as authoritative list math (per-token USD strings).
  • Respect context and feature flags before you enable tools or long prompts in production.

Previous: Authentication. Next: Chat completions.

AuthenticationChat completions