Watch · checked weekly

What models does Amp’s new ChatGPT-linked subscription actually include?

Answer from Aug 18

An earlier version of this page. The current answer may differ.

See the current answer →

Checked 10 times since Jul 28 · paused

The answer then

Sources

History

100 50 0 Jul 28: 90/100 Aug 4: 90/100 Aug 11: 64/100 Aug 18: 67/100 · the answer changed Aug 25: 75/100 · the answer changed Sep 1: 90/100 Sep 8: 62/100 Sep 15: 29/100 Sep 29: 64/100 · the answer changed Jul 28, 2026 Sep 29, 2026
How strongly the models agree, per check. Filled points mark checks that changed the answer.
  1. The answer changed

    The old consensus stated that High dial and Oracle use GPT-6 Astra. The new consensus reverses this, stating that Low uses GPT-5.6 Terra, Medium uses GPT-5.6 Sol, and High uses GPT-5.6 Sol, while acknowledging GPT-6 Astra as a future or changing documentation name. This is a material shift in specific model assignments.

    Read this version
  2. The answer changed

    The routing models have fundamentally shifted. The old consensus stated that ChatGPT linking covers GPT-5.6 Terra and GPT-5.6 Sol, while Ultra and others are excluded. The new consensus updates this to include GPT-6 Astra for High-mode and Oracle roles (depending on the ChatGPT tier), replacing the older GPT-5.6 assignments for those tiers.

    Read this version
  3. 3 checks, no change
  4. The answer changed

    The exact model routing breakdown substantially changed: Low main agent shifted from GLM-5.2 to GPT-5.6 Terra, High oracle shifted from Claude Fable 5 to GPT-5.6 Sol, and Code review shifted from GPT-5.5 to GPT-5.6 Terra. Additionally, the new answer specifies that Low/Med/High workflows are covered, while Ultra mode uses Claude Fable and Amp credits.

    Read this version
  5. The answer changed

    The breakdown of model assignments per routing mode changed significantly. Low mode changed from GPT-5.6 Terra to GLM-5.2 + GPT-5.6 Sol; High mode oracle changed from GPT-5.6 Sol to Claude Fable 5; Review changed from GPT-5.6 Terra to GPT-5.5; and specific routes for Puck/Search and Librarian were added while general routing details were updated.

    Shown above
  6. 2 checks, no change
  7. Watch started

    The first answer. Every later check is compared with it.

    Read this version
How the 3 models compared · 2 contradictions

OpenAI GPT-5.6 Luna · Google Gemini Gemini 3.7 Flash · Grok Grok 4.3

contradiction · minor detail

Whether Low mode replaces GLM-5.2 with GPT-5.6 Terra when ChatGPT is linked.

Low mode agent switches from GLM-5.2 to GPT-5.6 Terra with a linked ChatGPT sub.

Gemini, Grok

“(serving as the main fast agent, replacing the default GLM-5.2).”

Low mode main agent remains GLM-5.2 with GPT-5.6 Sol as oracle.

OpenAI

How to verify: Check Amp's latest modes documentation regarding model routing for Low mode with a linked ChatGPT account.

contradiction · minor detail

Whether High mode oracle uses GPT-5.6 Sol or Claude Fable 5 with a linked ChatGPT sub.

High mode uses GPT-5.6 Sol for both main agent and oracle when ChatGPT is linked.

Gemini, Grok

“the main agent (with extra-high reasoning) and the auxiliary Oracle”

High mode oracle continues to use Claude Fable 5.

OpenAI

How to verify: Check Amp's routing settings for High mode oracle under a linked ChatGPT plan.