Models

Reasoning model

For the core reasoning model, Antigravity offers leading frontier models. Availability depends on your plan:

Model	Free & Google AI Plus	Google AI Pro	Google AI Ultra	Enterprise
Gemini 3.8 Flash	✅	✅	✅	✅
Gemini 3.7 Flash	✅	✅	✅	✅
Gemini 3.6 Flash	✅	✅	✅	✅
Gemini 3.1 Pro	✅	✅	✅	✅
Claude Sonnet 4.6 (thinking)	✅	✅	✅	❌
Claude Opus 4.6 (thinking)	✅	✅	✅	❌
GPT-OSS-120b	✅	✅	✅	❌

You can select which reasoning model you want to use from the model selector menu under the conversation prompt box:

Model

Gemini 3.8 FlashMedium

Fast

LowMediumHigh

Gemini 3.7 FlashMedium

Fast

LowMediumHigh

Gemini 3.6 FlashMedium

Fast

LowMediumHigh

Gemini 3.1 ProHigh

LowHigh

Claude Sonnet 4.6 (Thinking)

Claude Opus 4.6 (Thinking)

GPT-OSS 120B (Medium)

View Usage

Gemini Models

Weekly Limit Remaining

100%

Five Hour Limit Remaining

100%

Claude and GPT models

Weekly Limit Remaining

100%

Five Hour Limit Remaining

100%

Your choice of reasoning model persists between messages within a conversation. If you change the reasoning model while the agent is running, it continues to use the previously selected reasoning model until it completes its steps for that turn (or until you cancel the current execution).

To learn more about reasoning model rate limits, refer to the plans page.

Additional models

Antigravity uses other models for various parts of the stack that aren’t customizable:

• Nano Banana 2: Used by the generative image tool when the agent produces a UI mockup, generates images to populate a web page or application, creates system or architecture diagrams, or performs other generative image tasks.