Build a Dated Model Access Ledger by Region, Tier and API Surface. This dated guide separates the actual model or API mechanism from promotional comparisons, endpoint aliases and features added by later releases. It focuses on implementable choices, documented limits and evidence a project should collect before deployment.
Cutoff: 25 October 2026 · Scope: publisher sources and editorial methods; account-specific features not independently verified.
What was released and when
A feature documented on a provider website may be unavailable to a specific user because of plan, organization verification, geographic restrictions, platform or preview enrollment. An accurate public model catalog therefore needs a dated entitlement ledger, not one global true/false field labelled available. The same named model may exist on a consumer chatbot, a cloud enterprise deployment and a direct API under different conditions.
Architecture, interface and the important distinction
A workable record has provider, family, public model string, alias-or-snapshot type, product surface, region, tier, account eligibility, as-of date, state (generally available, preview, waitlisted, deprecated, retired), quota unit and original source URL. Separate verified public statements from a customer-specific tenant observation. Keep unknown fields null rather than copying values from another country.
A useful real-world implementation
When a new model appears, check its dated launch announcement and API model reference, then verify the entitlement in an authorized deployment. Preserve the error response if a valid account receives model_not_found; that can indicate missing access rather than a nonexistent global model. Repeat the check after a planned alias migration or provider deprecation notice.
Limitations, licensing and evidence quality
Do not claim that an endpoint is live based on an old screenshot, an unofficial aggregator, or a current documentation page that has been rewritten. A trial, free usage tier and API credits are distinct products. Account-level availability must never be extrapolated from a researcher’s personal access.
Alternatives and the selection rule
Maintain an editorial access table for discovery and a private account entitlement table for operations. AI10 owns dated price snapshots, while AI12 owns integration and cross-site canonical identifiers.
Evaluation protocol worth running
QA should reject records without a checked_at date or where `public_model_id` is a product nickname passed off as an immutable string. Evaluate sampled rows monthly or at migration deadlines; store audit trails for every change.
Deployment and provenance checklist
Deployment record to preserve: canonical editorial ID wai-ai02-access-availability-ledger-by-tier, exact endpoint or checkpoint revision when verified, request date and region, model and tokenizer version, allowed tools, input modality, prompt template, output budget and actual measured usage. For current currency costs use the AI10 price snapshot matched by version, billing unit, region, tier and effective date. Unknown access entitlements must remain explicitly unknown.
Editorial evidence boundary
This is a 2026-10-25 editorial snapshot. A product or service may have changed after that date; the linked official pages can be edited without preserving every prior state. No independent model performance testing or live customer-account entitlement check was conducted for this article.
Sources & Further Reading
- Google Gemini models index (retrieved from first-party public documentation on 2026-10-25; this is not a deployment test)
- platform.claude.com — documentation/reference (supplier-provided reference; not independently checked in this pass)
Source documentation establishes vendor-published facts, not independently measured model quality, tenant access, contractual rights or current prices. Use a dated pricing ledger and an account-specific entitlement check for deployment decisions.