| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| InferHub | 7.49 s | 45.32 s | 54 tok/s | 98.7% | 49% |
| OpenAI direct | 1.67 s | 13.64 s | 180 tok/s | 99.8% | 47% |
| BlazeAPI | 18.42 s | 61.18 s | 40 tok/s | 92.0% | 3% |
| Venice AI direct | 3.04 s | 33.57 s | - | 98.9% | 1% |
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="gpt-6-astra", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1