| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| OpenRouter | 13.64 s | 45.32 s | 134 tok/s | 88.9% | 60% |
| Google Gemini API (AI Studio) direct | 7.49 s | 61.18 s | 180 tok/s | 90.4% | 40% |
Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.
Read the quickstart ↗from openai import OpenAI client = OpenAI( api_key="inf_your_key_here", base_url="$SURPLUS_BASE_URL" ) response = client.chat.completions.create( model="gemini-4-hydrogen", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1
