Skip to content
Open Source
Models/nvidia/llama-3.1-405b

Llama 3.1 405B Frontier NIM

ActiveZDR Certified
nvidia/llama-3.1-405b
Input / Prompt$0.00 / M
Output / Completion$0.00 / M
Context Window128K
Throughput Speed75 tps
3 Providers Serving This ModelDeterministic Failover Active
ProviderInput /MOutput /MLatency (TTFT)Speed (TPS)UptimeQuantizationZDRAction
NVIDIAPrimary Upstream
$0.00 / M$0.00 / M0.12s75 tps99.98%FP16YesConnect / Configure Provider →
OpenRouter (Edge Router)Multi-Region Backup
$0.00 / M$0.00 / M0.24s110 tps99.92%FP8YesConnect / Configure Provider →
Cerebras Cloud LPUInference Accelerator
$0.00 / M$0.00 / M0.04s2,100 tps99.85%INT8NoConnect / Configure Provider →