Switch models & read the agent's Artifacts

🎯Goal. Pick the right model for the job and verify what an agent did by reading the Artifacts it produces.

1. 1Antigravity is model-agnostic: from the model selector you can switch between Gemini (3.5 Flash, 3.1 Pro, 3 Flash), Anthropic Claude Sonnet & Opus 4.6, and gpt-oss-120b — all inside one platform. Try a stronger model on a hard task, a fast one for routine edits.
2. 2Instead of just editing files, agents produce Artifacts — task lists, screenshots and browser walkthroughs — so you can see at a glance what the agent did and leave feedback like comments on a doc.
3. 3Use Artifacts as your review step: skim the task list and screenshots, comment where something's off, and let the agent address it — your supervision is where the quality comes from, since agents act on your code.

✓You'll see. The same task run on a different model, plus Artifacts — a task list, screenshots, a browser walkthrough — that let you verify and comment on the agent's work.

💳Cost. All listed models are available on the free For Individuals plan ($0/month). For higher rate limits and a flexible AI credit pool, there are Google AI Pro and Google AI Ultra paid tiers — see antigravity.google/pricing for current pricing.

💡Takeaway. Match the model to the task and treat Artifacts as your review surface — that's how you stay in control of agents that act on your code.