Create a dedicated read nodes index

Create a Pinecone dedicated read nodes index from scratch or from a backup of an existing index.

From scratch

Create the index

Call Create an index. In the request body, in the spec.serverless.read_capacity object, set the following fields:

Field	Value	Notes
`mode`	`Dedicated`
`dedicated.node_type`	`b1` or `t1`	See node types
`dedicated.scaling`	`Manual`	The only supported value
`dedicated.manual.shards`	Number of shards needed	Minimum 1 shard; each shard provides 250 GB of storage
`dedicated.manual.replicas`	Number of replicas needed	Minimum 0 (this pauses the index)

This example creates an index with two shards and one replica:

Request

PINECONE_API_KEY="YOUR_API_KEY"

curl "https://api.pinecone.io/indexes" \
     -H "Accept: application/json" \
     -H "Content-Type: application/json" \
     -H "Api-Key: $PINECONE_API_KEY" \
     -H "X-Pinecone-Api-Version: 2025-10" \
     -d '{
           "name": "example-dedicated-index",
           "dimension": 1024,
           "metric": "cosine",
           "deletion_protection": "enabled",
           "tags": {
             "environment": "production"
           },
           "vector_type": "dense",
           "spec": {
             "serverless": {
               "cloud": "aws",
               "region": "us-east-1",
               "read_capacity": {
                 "mode": "Dedicated",
                 "dedicated": {
                   "node_type": "b1",
                   "scaling": "Manual",
                   "manual": {
                     "shards": 2,
                     "replicas": 1
                   }
                 }
               }
             }
           }
         }'

Show 24 more linesShow less

Response

{
  "name": "example-dedicated-index",
  "vector_type": "dense",
  "metric": "cosine",
  "dimension": 1024,
  "status": {
    "ready": false,
    "state": "Initializing"
  },
  "host": "example-dedicated-index-1c6ab6aa.svc.aped-4627-b74a.pinecone.io",
  "spec": {
    "serverless": {
      "region": "us-east-1",
      "cloud": "aws",
      "read_capacity": {
        "mode": "Dedicated",
        "dedicated": {
          "node_type": "b1",
          "scaling": "Manual",
          "manual": {
            "shards": 2, // <---- desired state
            "replicas": 1
          }
        },
        "status": {
          "state": "Migrating",
          "current_shards": null, // <---- current state
          "current_replicas": null
        }
      }
    }
  },
  "deletion_protection": "enabled",
  "tags": {
    "environment": "production"
  }
}

Show 27 more linesShow less

The response includes two status fields:

Field	Description
`status.state`	Overall index status (for example, `Initializing`, `Ready`, `Terminating`)
`spec.serverless.read_capacity.status.state`	Read capacity status (`Migrating`, `Scaling`, `Ready`, `Error`)

Add your data
After the index is created, upsert or import your data.
To upsert and search with text instead of vectors, you can configure your index to use a hosted embedding model. Call Configure an index and specify the embed object in the request body.

From a backup

Restore the backup
Restore the backup to a new on-demand index with the same data as the original.
Delete extra namespaces
If the restored index has multiple namespaces, delete all of them except the one you want to keep. Dedicated read nodes support only one namespace.
Migrate to dedicated read nodes
Convert the restored on-demand index by following Migrate to dedicated read nodes.