Inference

Inference Queue

OpenAI-compatible. Queued, routed, signed. Chat, voice, image, and video. One key.

Family
Service
Role
stream
Interface
API
Availability
Live
Address
queue.inference.drm3.network
Overview

The OpenAI-compatible inference queue in front of DRM3's inference backends. An end user gets an API key and a standard chat completions endpoint; calls are queued, routed, signed and metered by the ledger.

Services

More from the platform.

All 13 services →