Gemini 3.8 Flash Is Now the Only Gemini Model in My Antigravity Selector. Here’s What I Can (and Can’t) Confirm

Описание и применение

В Antigravity исчезла модель Gemini 3.1 Pro, оставив только Gemini 3.8 Flash, что ускорило выполнение задач и сократило потребление квоты, но лишило разработчиков более мощного варианта.

Задача

The sudden disappearance of Gemini 3.1 Pro from the Antigravity model selector left developers without a known fallback and raised questions about model availability and deprecation.

Результат

Gemini 3.8 Flash delivers faster turnaround (3–6 s vs. 28–45 s), lower quota consumption (~11 % vs. ~42 %), and fewer refactoring iterations (1 vs. 3) on a complex Excel automation task, but the loss of 3.1 Pro removes a higher‑reasoning option for developers.

Рабочий процесс

• Open Antigravity model selector
• Observe only Gemini 3.8 Flash listed
• Verify 3.1 Pro is absent
• Check Google AI Developers Forum for reports
• Review official documentation for deprecation status
• Compare performance metrics between 3.1 Pro and 3.8 Flash on a real automation task
• Document latency, quota, and iteration differences

Доказательства

In my Antigravity client (Plan: Google AI Pro), Gemini 3.1 Pro is no longer selectable. The only native Gemini entry point is Gemini 3.8 Flash across all thinking tiers (Low, Medium, High).

Источник

Multiple subscribers on the Google AI Developers Forum reported that 3.1 Pro disappeared abruptly after a recent platform sync, sparking immediate calls to bring the model back.

Источник

Turnaround Latency: 28 to 45 seconds per agent step for 3.1 Pro vs. 3 to 6 seconds per step for 3.8 Flash High.

Источник

Consumed ~11% of quota for the entire completed routine (3.8 Flash) vs. ~42% of the 5‑hour rate limit (3.1 Pro).

Источник