SCX AI · OpenAI-Compatible Engines
Meta's 400B MoE (17B active, 128 experts) with native multimodal early fusion supporting 12 languages and images. 128k context.
A capable all-rounder — the sensible default for everyday assistant and agent work.
Free
No per-token charge at present. Providers can change pricing — this page tracks the published rate.
Model id: Llama-4-Maverick-17B-128E-Instruct
The platform default — used automatically when no other provider is connected.
Get an API key and point your first request at ApiSpi in minutes