All integrationsCloud Computing

CoreWeave

Manage inference deployments, gateways, capacity claims and checkpoint hot-loads.

actions
20
triggers
6

Triggers

Start a workflow when something happens in CoreWeave.

  • New deploymentRuns for each new deployment in CoreWeave. Ones already there when the workflow is turned on don't start it. It can watch up to 4,000. How often it checks follows your workspace plan.
  • Deployment status changedRuns each time a deployment status changes in CoreWeave. Changes made before the workflow is turned on don't start it. It can watch up to 4,000. How often it checks follows your workspace plan.
  • New gatewayRuns for each new gateway in CoreWeave. Ones already there when the workflow is turned on don't start it. It can watch up to 4,000. How often it checks follows your workspace plan.
  • New capacity claimRuns for each new capacity claim in CoreWeave. Ones already there when the workflow is turned on don't start it. It can watch up to 4,000. How often it checks follows your workspace plan.
  • New checkpoint hot-loadRuns for each new checkpoint hot-load in CoreWeave. Ones already there when the workflow is turned on don't start it. It can watch up to 4,000. How often it checks follows your workspace plan.
  • Hot-load replica state changedRuns each time a hot-load replica state changes in CoreWeave. Changes made before the workflow is turned on don't start it. It can watch up to 4,000. How often it checks follows your workspace plan.

Actions

Steps a workflow can run in CoreWeave.

  • List deploymentsReturns every deployment that the caller can read, optionally filtered by parent gateway or update timestamp.
  • Get deploymentRetrieves a single deployment by ID.
  • Create deploymentCreates a new model deployment associated with one or more gateways.
  • Update deploymentUpdates an existing deployment. The request body replaces the deployment's spec; this endpoint does not accept a field mask.
  • Delete deploymentDeletes a deployment by ID. Returns the deleted deployment.
  • Get deployment parametersReturns the available gateways, runtime engines and versions, runtime config keys, and instance types for use when creating a deployment.
  • List gatewaysReturns every inference gateway that the caller can read, optionally filtered by update timestamp.
  • Get gatewayRetrieves a single gateway by its UUID.
  • Create gatewayCreates a new inference gateway. Each gateway must be configured with exactly one authentication type and exactly one routing strategy.
  • Update gatewayUpdates an existing gateway. The request body replaces the gateway's spec; this endpoint does not accept a field mask.
  • Delete gatewayDeletes a gateway by ID. Returns the deleted gateway.
  • List capacity claimsReturns every CapacityClaim that the caller can read.
  • Get capacity claimRetrieves a single CapacityClaim by its UUID.
  • Create capacity claimCreates a new CapacityClaim that reserves GPU hardware for inference deployments.
  • Delete capacity claimDeletes a CapacityClaim by ID. Returns the deleted CapacityClaim.
  • List checkpoint hot-loadsReturns the caller's hot-loads, newest first, optionally filtered to a single deployment.
  • Get checkpoint hot-loadReturns a hot-load by ID, including its resolved snapshot chain and aggregate state.
  • Create checkpoint hot-loadTriggers a checkpoint hot-load on a deployment. The operation runs asynchronously, so a successful response means the request was accepted, not that the weights are loaded.
  • List hot-load replicasReturns the replicas of one hot-load, ordered by zone and name, in pages.
  • Cancel checkpoint hot-loadCancels a hot-load. This operation is not yet implemented and currently returns an Unimplemented error.

Automate CoreWeave with Lodol.

Connect CoreWeave, then hand Lodol the job in Slack, Claude or ChatGPT.

We’re letting people in a few at a time.