M
MERIDIAN

Lambda Labs Inference (alt) with Meridian

Point Meridian at your Lambda Labs GPU instances and get automatic load balancing, request queuing, and per-model cost tracking without touching your inference code.

< 2ms
Latency overhead
< 50ms
Failover time
Any
Supported models

Quick setup

  1. 1Add your Lambda Labs API key in the Meridian dashboard.
  2. 2Register your GPU instance endpoints.
  3. 3Swap your base URL to https://meridian.example.com/v1
← All integrationsAdvanced config →