| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| Google Gemini API (AI Studio) direct | 18.42 s | 150.53 s | 99 tok/s | 91.0% | 81% |
| OpenRouter | 18.42 s | 111.50 s | 73 tok/s | 94.9% | 17% |
| Venice AI direct | 18.42 s | 82.59 s | - | 98.2% | 2% |
| InferHub | 24.87 s | - | - | 25.3% | 0% |
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-carbon", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1
