Antigravity Agent Preview
Antigravity Agent Preview on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
At a glance.
| Provider | |
| Family | gemini |
| Released | — |
| License | Proprietary |
| Context window | 131K tokens |
| Max output | 66K tokens |
| Modalities | text, image |
| Tool calling | Yes |
| Reasoning mode | No |
| Caching | none |
| Batch discount | 50% off |
What reuse looks like here.
Pricing, context, and capabilities for Antigravity Agent Preview are live, but it is outside the flagship set Zumik benchmarks in depth, so measured reuse, capture, and warm TTFT are not shown yet. Run a workload estimate or route it by id to start collecting traces.
Same OpenAI client, this model.
from openai import OpenAI
client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")
r = client.responses.create(
model="antigravity-preview-05-2026",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseAntigravity Agent Preview, answered.
How much does Antigravity Agent Preview cost?
Antigravity Agent Preview is an open-weights model routed through Google Gemini. It is priced on the host's serverless size tier rather than a single published per-token list price, so it shows "—" here until profiled.
What is Antigravity Agent Preview's context window?
Antigravity Agent Preview supports a 131K-token context window with up to 66K output tokens.
Run Antigravity Agent Preview with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.