Model Reference

Locally maintained, multi-source quick reference for AI model specifications, lifecycle, callable IDs, pricing, deployment constraints, and generation guidance.

This skill is not synchronized from a single provider. Each reference is a dated manual snapshot built from provider-primary documentation, official repositories/model cards, release announcements, and technical reports.

Hard Rules

• MUST open the relevant file in references/ before answering model IDs, lifecycle, context/output limits, pricing, sampling parameters, benchmark scores, licenses, or memory requirements.
• MUST state the reference's Last verified date when the answer depends on volatile data such as aliases, preview status, pricing, limits, or deprecation.
• MUST distinguish API aliases from pinned snapshots and app/product names from callable API model IDs.
• MUST distinguish native context from provider-extended context and synchronous output limits from batch/long-output modes.
• MUST qualify pricing by provider, unit, prompt tier, cache/batch state, and region when applicable.
• MUST label benchmarks as vendor-reported unless an independent primary evaluation source and setup are cited. Do not treat different benchmark settings as directly comparable.
• MUST distinguish total parameters from active parameters. NEVER estimate MoE weight residency from active parameters alone unless expert offload is an explicit assumption.
• MUST verify official provider docs before production decisions when a reference is older than 30 days or marks a model preview/deprecated.
• NEVER invent model IDs, release dates, context/output limits, prices, knowledge cutoffs, licenses, or generation settings.

Fast Lookup