Create a legacy integrated index

Create a legacy integrated index. Legacy integrated indexes created via create-for-model require the legacy Records API.

For new work, create a document index with Create an index, declaring embed or sparse_embed on a string field to enable integrated embedding on it, and read and write the index through the Documents API. Document indexes support integrated embedding alongside full-text search on the same field, and scoring with score_by.

With this type of index, you provide source text, and Pinecone uses a hosted embedding model to convert the text automatically during upsert and search.

The response is this version’s index model, with the embedding configuration surfaced as a semantic_text field in the index schema, named after the field_map text entry. Read and write the index through the legacy Records API.

For guidance and examples, see Create an index.

POST /indexes/create-for-model

Python

# pip install --upgrade pinecone
import os
from pinecone import Pinecone

pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])

index_model = pc.indexes.create_for_model(
    name="docs-example",
    cloud="aws",
    region="us-east-1",
    embed={
        "model": "multilingual-e5-large",
        "field_map": {"text": "chunk_text"},
    },
)

201

Example

{
  "deletion_protection": "disabled",
  "deployment": {
    "cloud": "aws",
    "deployment_type": "managed",
    "region": "us-east-1"
  },
  "host": "my-index-abc123.svc.pinecone.io",
  "name": "my-index",
  "read_capacity": {
    "mode": "OnDemand",
    "status": {
      "state": "Ready"
    }
  },
  "schema": {
    "fields": {
      "title": {
        "full_text_search": {
          "language": "en",
          "stemming": false,
          "stop_words": false
        },
        "store_text": true,
        "type": "string"
      },
      "your_vector": {
        "dimension": 1536,
        "metric": "cosine",
        "type": "dense_vector"
      }
    }
  },
  "status": {
    "ready": true,
    "state": "Ready"
  }
}

Python

# pip install --upgrade pinecone
import os
from pinecone import Pinecone

pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])

index_model = pc.indexes.create_for_model(
    name="docs-example",
    cloud="aws",
    region="us-east-1",
    embed={
        "model": "multilingual-e5-large",
        "field_map": {"text": "chunk_text"},
    },
)

Authorizations

Api-Key · string · header · required

An API Key is required to call Pinecone APIs. Get yours from the console.

Headers

X-Pinecone-Api-Version · string · default: 2026-07 · required

Required date-based version header

Body

application/json

The desired configuration for the index and associated embedding model.

name · string · required

The name of the index. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or '-'.

Required string length: 1 - 45

Example:

"example-index"

cloud · string · required

The public cloud where you would like your index hosted.

Possible values: gcp, aws, or azure.

Example:

"aws"

region · string · required

The region where you would like your index to be created.

Example:

"us-east-1"

embed · object · required

Specify the integrated embedding configuration for the legacy integrated index.

Once set the model cannot be changed, but you can later update the embedding configuration of a legacy integrated index, including field map, read parameters, or write parameters.

Refer to the model guide for available models and model details.

Show child attributes

Example:

{
  "field_map": { "text": "your-text-field" },
  "metric": "cosine",
  "model": "multilingual-e5-large",
  "read_parameters": { "input_type": "query", "truncate": "NONE" },
  "write_parameters": { "input_type": "passage" }
}

deletion_protection · string · default: disabled

Whether deletion protection is enabled/disabled for the index.

Possible values: disabled or enabled.

tags · object | null

Custom user tags added to an index, at most 20 per index. Keys must be 80 characters or less and alphanumeric, '_', or '-'. Values must be 120 characters or less and consist of printable ASCII characters or spaces. To unset a key, set the value to be an empty string. null in responses when the index has no tags.

Show child attributes

Example:

{ "tag0": "val0", "tag1": "val1" }

schema · object

Schema for the behavior of Pinecone's internal metadata index. By default, all metadata is indexed; when schema is present, only fields which are present in the fields object with a filterable: true are indexed. Note that filterable: false is not currently supported.

Show child attributes

Example:

{
  "fields": {
    "description": { "filterable": true },
    "genre": { "filterable": true },
    "year": { "filterable": true }
  }
}

read_capacity · On-demand · object

By default the index will be created with read capacity mode OnDemand. If you prefer to allocate dedicated read nodes for your workload, you must specify mode Dedicated and additional configurations for node_type and scaling. BYOC indexes do not support OnDemand: a byoc deployment must set mode: Dedicated explicitly, since omitting read_capacity defaults to OnDemand and is rejected.

On-demand

Dedicated

Show child attributes

Example:

{ "mode": "OnDemand" }

Response

201

application/json

The index has successfully been created for the embedding model.

The IndexModel describes the configuration and status of a Pinecone index.

name · string · required

The name of the index. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or '-'.

Required string length: 1 - 45

Example:

"example-index"

host · string · required

The URL address where the index is hosted.

Example:

"semantic-search-c01b5b5.svc.us-west1-gcp.pinecone.io"

status · object · required

The current status of the index.

Show child attributes

Example:

{ "ready": true, "state": "Ready" }

deployment · Pod-based · object · required

The deployment configuration of a Pinecone index. The deployment_type field indicates which infrastructure model the index uses.

• pod: Dedicated pod-based infrastructure. Suitable for workloads that require predictable performance.
• managed: Serverless infrastructure managed by Pinecone, including full-text search indexes. Scales automatically; billed per usage.
• byoc: Bring-your-own-compute. Runs in customer-managed infrastructure.

Pod-based

Serverless

BYOC

Show child attributes

Example:

{
  "deployment_type": "pod",
  "environment": "us-east1-gcp",
  "pod_type": "p1.x1",
  "replicas": 1,
  "shards": 1
}

schema · object · required

The schema of a Pinecone index. The schema defines the typed fields that documents in the index can contain, including vector fields, string fields searched by full-text search or by embeddings, and metadata fields.

Show child attributes

Example:

{
  "fields": {
    "body": {
      "embed": {
        "dimension": 1024,
        "metric": "cosine",
        "model": "llama-text-embed-v2"
      },
      "full_text_search": {
        "language": "en",
        "stemming": false,
        "stop_words": false
      },
      "sparse_embed": { "model": "pinecone-sparse-english-v0" },
      "store_text": true,
      "type": "string"
    },
    "title": {
      "full_text_search": {
        "language": "en",
        "stemming": false,
        "stop_words": false
      },
      "store_text": true,
      "type": "string"
    }
  }
}

deletion_protection · string · default: disabled · required

Whether deletion protection is enabled/disabled for the index.

Possible values: disabled or enabled.

private_host · string

The private endpoint URL of an index.

Example:

"semantic-search-c01b5b5.svc.private.us-west1-gcp.pinecone.io"

read_capacity · On-demand · object

Response containing read capacity configuration

On-demand

Dedicated

Show child attributes

Example:

{
  "mode": "OnDemand",
  "status": { "state": "Ready" }
}

source_collection · string

The name of the collection this index was created from, if any.

Example:

"movie-embeddings"

source_backup_id · string

The ID of the backup this index was restored from, if any.

Example:

"670e8400-e29b-41d4-a716-446655440000"

cmek_id · string

The ID of the customer-managed encryption key (CMEK) used to encrypt this index, if any.

Example:

"arn:aws:kms:us-east-1:123456789012:key/mrk-abc123"

tags · object | null

Custom user tags added to an index, at most 20 per index. Keys must be 80 characters or less and alphanumeric, '_', or '-'. Values must be 120 characters or less and consist of printable ASCII characters or spaces. To unset a key, set the value to be an empty string. null in responses when the index has no tags.

Show child attributes

Example:

{ "tag0": "val0", "tag1": "val1" }