specialty

SambaNova

RDU inference for large OSS models with enterprise SLAs.

live

Uptime (30d)

99.8%

Median tps

520

Median TTFT

60 ms

Price index

0.8×

vs. market median

Overview

HQ: Palo Alto, US
Founded: 2017
Models: 10
Modalities: text, vision
Regions: us-west, eu-west

Strengths

throughputenterprise

Route via llmcloud

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