open source-host

RunPod

GPU spot capacity with serverless endpoints.

beta

Uptime (30d)

99.5%

Median tps

130

Median TTFT

220 ms

Price index

0.4×

vs. market median

Overview

HQ: Delaware, US
Founded: 2022
Models: 30
Modalities: text, image
Regions: us-east, eu-west, asia-east

Strengths

cheap-gpuflexible

Route via llmcloud

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