open source-host

llmcloud OSS

Our own hosted open-weight fleet — tuned for throughput.

live

Uptime (30d)

99.9%

Median tps

260

Median TTFT

100 ms

Price index

0.35×

vs. market median

Overview

HQ: Bay Area, US
Founded: 2024
Models: 22
Modalities: text, vision
Regions: us-east, us-west, eu-west

Strengths

cheapthroughputfine-tuning

Route via llmcloud

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