Clusters

Manage your GPU inference clusters

New Cluster
ClusterGPUReplicasTierRegionStatusCost/hr

prod-inference

cl_5090_prod

RTX 5090

32GB

4Verifiedus-east-1running$3.30

staging-llm

cl_4090_stag

RTX 4090

24GB

2Verifiedus-west-2running$1.20

dev-vision

cl_3090_dev

RTX 3090

24GB

1Communityeu-west-1stopped$0.00

test-embeddings

cl_4090_test

RTX 4090

24GB

1Communityus-east-1deploying$0.40