Limited-access models

Some models require elevated provider-account access. What that means, why some calls fail with a 403, and how to upgrade.

Updated 2026-04-25 · By Jonathan Lasley

A small number of provider models require elevated account access beyond a standard API key. The model picker marks these with a Limited access badge and a tooltip; selecting one is allowed, but the LLM call will fail with a 403 Forbidden if your provider account doesn't qualify.

Which models

As of April 2026, the limited-access models in Prompt Assay are:

`gpt-5.5-pro` -- OpenAI's highest-precision GPT-5.5 variant. Background mode only (no streaming).
`gpt-5.4-pro` -- OpenAI's enhanced-precision GPT-5.4 variant.

Why these models specifically

OpenAI's 'pro' variants are gated by account tier, not by an opt-in form. Higher tiers unlock larger rate limits and access to the -pro family. The standard non-pro models (gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano) are available to every paid OpenAI account.

What happens when access is denied

If you select a limited-access model and your account isn't entitled, the LLM call returns a 403 from the provider. Prompt Assay surfaces a clear error in the panel telling you the model is gated and linking back to this article. Your BYOK key is not the problem -- the key is valid; the model just isn't on your account's allowed list.

How to upgrade

Open the OpenAI dashboard and check your usage tier (Tier 1 through Tier 5).
Tier eligibility is automatic based on lifetime spend on your OpenAI account. Tier 1 typically requires ~$5 of lifetime usage; higher tiers need more.
Once you're on a tier that includes the -pro family, the model becomes immediately available on the same API key -- no key rotation needed.

Pricing reminder

Limited-access models are typically 6-12x more expensive than the standard variants. gpt-5.5-pro is $30 input / $180 output per 1M tokens vs gpt-5.5 at $5 / $30. The cost-estimate UI surfaces this before you run; double-check it on long prompts.

Other 'limited-access' situations (none today)

The badge pattern is reusable. If a future model -- from any provider -- requires special access (a feature opt-in, an enterprise contract, a specific account tier), it will surface here under the same Limited access badge with the same tooltip pointing back to this page. As of April 2026, only the two OpenAI pro variants above qualify.

← All docs Open the editor →