| Route | p50 latency | p95 latency | Success rate | ShareShare of traffic |
|---|---|---|---|---|
| Google Gemini API (AI Studio) direct | 679 ms | - | 58.7% | 100% |
| InferHub | - | - | 0.0% | 0% |
Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.
Read the quickstart ↗import os import requests response = requests.post( "$SURPLUS_BASE_URL/images/generations", headers={"Authorization": f"Bearer {os.environ['SURPLUS_API_KEY']}"}, json={"model": "gemini-2.5-flash-image", "prompt": "A lighthouse at dusk"}, )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1