specialty

Cerebras

Wafer-scale inference; fastest tokens/sec for Llama-70B class.

live

Uptime (30d)

99.6%

Median tps

950

Median TTFT

35 ms

Price index

0.9×

vs. market median

Overview

HQ: Sunnyvale, US
Founded: 2016
Models: 8
Modalities: text
Regions: us-west

Strengths

ultra-low-latency

Route via llmcloud

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