Models
The shared model catalog and BYOK provider boundaries.
Alumia exposes a shared app model picker with 37 visible models across 14 providers. The full internal catalog tracks 39 model entries across 14 providers. Each agent is configured with one supported model, and you can change that model when the workflow calls for a different balance of quality, speed, and cost.
Managed models
With managed models, Alumia handles provider credentials, request routing, retries, streaming, and metering behind the product surface. Public copy should describe this as managed model reliability, not expose internal route details.
Current visible catalog examples include GPT-5.4, Claude Sonnet 4.6, GPT OSS 120B, MiMo V2 Pro, and NVIDIA Llama 3.3 Nemotron Super 49B. Internal route metadata also retains withdrawn entries such as GPT-5.5 and NVIDIA Nemotron 3 Super 120B A12B for safe migration and fallback. The visible catalog is validated before deploy so provider-specific model regressions are caught before users hit chat, artifacts, or agent execution.
BYOK models
Bring Your Own Key lets you add supported provider keys. When a BYOK key is active, Alumia uses it with the matching supported provider paths by default and records those requests as BYOK.
BYOK supported with matching provider paths means an active OpenAI, Anthropic, Gemini, Groq, Cerebras, NVIDIA, or compatible key is used for the matching supported model family while the user-facing model picker stays provider-agnostic.