What models does Amp’s new ChatGPT-linked subscription actually include?
Historical consensus 2026-09-01Active
Runs Weekly on Tuesday at 09:00 (Europe/Berlin)LastNext
Movement at this check
Changed since last check
The answer itself held, but the models now agree more than in the recent checks (+15 pts). The response was reformatted from a table to bullet points with slightly streamlined wording, but all core facts, covered models, modes, and exclusions remain identical.
Amp’s ChatGPT-linked subscription covers these OpenAI models for the specified modes:
GPT-5.6 Terra — Low mode, thread reading, and code review.
GPT-5.6 Sol — Medium mode, plus both the main agent and oracle in High mode.ampcode
This is mode-based routing, not access to every model Amp offers. Ultra is excluded: it continues to use Claude Fable and is charged against Amp credits rather than your ChatGPT subscription.ampcodeampcode
So, in short: Terra and Sol are covered; Claude Fable in Ultra is not. The linked subscription covers the applicable model calls through ChatGPT rather than Amp’s per-use credits.
Differences
The 3 models broadly agree – no notable differences found.
Best answerDeepSeek
Follow this question
This page is re-checked weekly. Get one e-mail when the AI consensus shifts — no account needed.
Double opt-in · unsubscribe anytime · your address is only used for these updates.
Since tracking began: The model coverage mappings have changed: GPT-5.6 Terra is now explicitly covered for 'low' mode (previously stated as GLM-5.2 and excluded), and specific coverage rules for thread reading, code review, and High mode components are updated while omitting other previously listed non-covered models and plan tiers.
View the full agreement chart
Agreement over time
How strongly the models support the same claims. Every point links to its run below.
Checks
Newest first. Open any saved result to read the full consensus from that date.
Meaningful change
90/100 agreement
The response was reformatted from a table to bullet points with slightly streamlined wording, but all core facts, covered models, modes, and exclusions remain identical.
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.
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.
The new answer provides more specific details about how the GPT-5.6 variants (Terra and Sol) map to different Amp usage modes (Low, Medium, High) and clarifies that non-OpenAI routes like Claude Fable 5 in Ultra mode are excluded.
3 AI models
answered this question independently on 2026-09-01. A judge from a different model family
then cross-checked the answers, scored how far they agree and flagged where they differ. The question is re-checked weekly, and every earlier version stays on this page.
AI models can make mistakes – verify important information against the sources above.
