Providers/CloudGPU
CloudGPU logo

CloudGPU

Inference providercloudgpu.app ↗
MODELS
16
ENDPOINTS
16
MIN INPUT
$0.135
MEDIAN BLENDED
$1.11
AVG UPTIME
—
CHEAPEST FOR
0 models
Models on CloudGPU · prices & measurements for models served by CloudGPU’s APIUSD / MTOK · VERIFIED 17 MINUTES AGO
MODELINPUTOUTPUTCONTEXTQUANTTTFTTPSVS BEST ELSEWHERE
Qwen logoQwen3.8 FlashQwen$0.135$0.4231M———$0.15 elsewhere
Z.ai logoGLM 5.3 FlashZ.ai$0.135$0.451.05M———$0.029 elsewhere
OpenAI logogpt-oss-120bOpenAI$0.135$0.54131K———$0.01 elsewhere
DeepSeek logoDeepSeek V4.1 FlashDeepSeek$0.27$1.081.05M———$0.006 elsewhere
DeepSeek logoDeepSeek V4 Flash 0423DeepSeek$0.27$1.081.05M———$0.045 elsewhere
MiniMax logoMiniMax M3MiniMax$0.281$1.111.05M—✕✕$0.23 elsewhere
Qwen logoQwen3.6 35B A3BQwen$0.338$2.02262K———$0.01 elsewhere
Qwen logoQwen3.8 27BQwen$0.45$2.701.02M———$0.015 elsewhere
Qwen logoQwen3.5 397B A17BQwen$0.54$3.24262K———$0.39 elsewhere
Moonshot AI logoKimi K2.6Moonshot AI$0.855$3.60262K———$0.39 elsewhere
Moonshot AI logoKimi K2.5Moonshot AI$0.855$3.60262K———$0.49 elsewhere
Moonshot AI logoKimi K2.7 CodeMoonshot AI$0.90$3.80262K———$0.60 elsewhere
Z.ai logoGLM 5.2Z.ai$1.26$3.961.05M———$0.006 elsewhere
Z.ai logoGLM 5.1Z.ai$1.26$3.96205K———$0.90 elsewhere
DeepSeek logoDeepSeek V4 Pro 0423DeepSeek$1.31$3.561.05M———$0.86 elsewhere
Moonshot AI logoKimi K3Moonshot AI$2.86$14.321.05M———$0.155 elsewhere
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for CloudGPU’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page