| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| OpenRouter | 4.11 s | 18.42 s | 73 tok/s | 98.9% | 49% |
| Venice AI direct | 7.49 s | 45.32 s | 54 tok/s | 99.8% | 40% |
| InferHub | 10.11 s | 61.18 s | 99 tok/s | 85.8% | 9% |
| Mordiem | 7.49 s | 24.87 s | - | 98.6% | 2% |
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="deepseek-v4-flash", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1