specialty

Groq

LPU-based ultra-low latency for Llama / Qwen / Mixtral.

live

Uptime (30d)

99.7%

Median tps

780

Median TTFT

40 ms

Price index

0.7×

vs. market median

Overview

HQ: Mountain View, US
Founded: 2016
Models: 12
Modalities: text
Regions: us-central

Strengths

ultra-low-latencythroughput

Route via llmcloud

curl https://api.llmcloud.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMCLOUD_KEY" \
  -H "X-Provider: groq" \
  -d '{
    "model": "auto:quality",
    "messages": [{"role":"user","content":"hi"}]
  }'