| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| Groq direct | 204 ms | 2.25 s | 808 tok/s | 51.4% | 81% |
| AWS Bedrock | 916 ms | 10.11 s | 329 tok/s | 89.2% | 19% |
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="openai-gpt-oss-safeguard-20b", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1