> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.runtype.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.runtype.com/_mcp/server.

# Create Vectorize index

POST https://api.runtype.com/v1/integrations/vectorize/indexes/create
Content-Type: application/json

Create a new Vectorize index in a Cloudflare account using provided or stored credentials.

Reference: https://docs.runtype.com/api-reference/runtype-api/integrations/create-vectorize-index

## Authentication

- `Authorization` header (bearer token, required) — API key or Clerk session token

## Servers

- `https://api.runtype.com` (Production, default)
- `https://api.runtype-staging.com` (Staging)

## Request

### Body (application/json)

This endpoint expects an object.

- `dimensions` (double, required)
- `indexName` (string, required)
- `metric` (string, required)
- `accountId` (string, optional)
- `apiToken` (string, optional)
- `configId` (string, optional)
- `description` (string, optional)

## Response

### 201

Created Vectorize index

- `success` (boolean, required)
- `error` (string, optional)
- `index` (V1IntegrationsVectorizeIndexesCreatePostResponsesContentApplicationJsonSchemaIndex, optional, nullable)

## Errors

### 400 Bad Request Error

Missing or invalid parameters

- `error` (string, required)
- `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs.
- `details` (list of ErrorDetailsItems, optional)
- `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs.

### 401 Unauthorized Error

Unauthorized

- `error` (string, required)
- `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs.
- `details` (list of ErrorDetailsItems, optional)
- `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs.

### 403 Forbidden Error

Insufficient permissions

- `error` (string, required)
- `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs.
- `details` (list of ErrorDetailsItems, optional)
- `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs.

### 404 Not Found Error

Configuration not found

- `error` (string, required)
- `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs.
- `details` (list of ErrorDetailsItems, optional)
- `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs.

### 500 Internal Server Error

Internal server error

- `error` (string, required)
- `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs.
- `details` (list of ErrorDetailsItems, optional)
- `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs.

## Types

### V1IntegrationsVectorizeIndexesCreatePostResponsesContentApplicationJsonSchemaIndex

- `dimensions` (double, required)
- `metric` (string, required)
- `name` (string, required)
- `vectorCount` (double, optional)

### ErrorDetailsItems

- `message` (string, required)
- `code` (string, optional) — Stable Runtype validation code (e.g. MISSING_REQUIRED_FIELD, INVALID_ENUM).
- `path` (string, optional) — Dotted JSON path to the offending field.
- `suggestion` (string, optional) — Actionable hint (allowed values, accepted range, …).

## Examples

**Request**

```json
{
  "dimensions": 1536,
  "indexName": "new-embeddings",
  "metric": "cosine",
  "accountId": "abcdef1234567890abcdef1234567890",
  "apiToken": "cf-api-token-here",
  "description": "Embeddings for document search"
}
```

**Response**

```json
{
  "success": true,
  "error": "string",
  "index": {
    "dimensions": 1.1,
    "metric": "string",
    "name": "string",
    "vectorCount": 1.1
  }
}
```

**SDK Code**

```python Create a new Vectorize index
import requests

url = "https://api.runtype.com/v1/integrations/vectorize/indexes/create"

payload = {
    "dimensions": 1536,
    "indexName": "new-embeddings",
    "metric": "cosine",
    "accountId": "abcdef1234567890abcdef1234567890",
    "apiToken": "cf-api-token-here",
    "description": "Embeddings for document search"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript Create a new Vectorize index
const url = 'https://api.runtype.com/v1/integrations/vectorize/indexes/create';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"dimensions":1536,"indexName":"new-embeddings","metric":"cosine","accountId":"abcdef1234567890abcdef1234567890","apiToken":"cf-api-token-here","description":"Embeddings for document search"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go Create a new Vectorize index
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.runtype.com/v1/integrations/vectorize/indexes/create"

	payload := strings.NewReader("{\n  \"dimensions\": 1536,\n  \"indexName\": \"new-embeddings\",\n  \"metric\": \"cosine\",\n  \"accountId\": \"abcdef1234567890abcdef1234567890\",\n  \"apiToken\": \"cf-api-token-here\",\n  \"description\": \"Embeddings for document search\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby Create a new Vectorize index
require 'uri'
require 'net/http'

url = URI("https://api.runtype.com/v1/integrations/vectorize/indexes/create")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"dimensions\": 1536,\n  \"indexName\": \"new-embeddings\",\n  \"metric\": \"cosine\",\n  \"accountId\": \"abcdef1234567890abcdef1234567890\",\n  \"apiToken\": \"cf-api-token-here\",\n  \"description\": \"Embeddings for document search\"\n}"

response = http.request(request)
puts response.read_body
```

```java Create a new Vectorize index
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.runtype.com/v1/integrations/vectorize/indexes/create")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"dimensions\": 1536,\n  \"indexName\": \"new-embeddings\",\n  \"metric\": \"cosine\",\n  \"accountId\": \"abcdef1234567890abcdef1234567890\",\n  \"apiToken\": \"cf-api-token-here\",\n  \"description\": \"Embeddings for document search\"\n}")
  .asString();
```

```php Create a new Vectorize index
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.runtype.com/v1/integrations/vectorize/indexes/create', [
  'body' => '{
  "dimensions": 1536,
  "indexName": "new-embeddings",
  "metric": "cosine",
  "accountId": "abcdef1234567890abcdef1234567890",
  "apiToken": "cf-api-token-here",
  "description": "Embeddings for document search"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp Create a new Vectorize index
using RestSharp;

var client = new RestClient("https://api.runtype.com/v1/integrations/vectorize/indexes/create");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"dimensions\": 1536,\n  \"indexName\": \"new-embeddings\",\n  \"metric\": \"cosine\",\n  \"accountId\": \"abcdef1234567890abcdef1234567890\",\n  \"apiToken\": \"cf-api-token-here\",\n  \"description\": \"Embeddings for document search\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift Create a new Vectorize index
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "dimensions": 1536,
  "indexName": "new-embeddings",
  "metric": "cosine",
  "accountId": "abcdef1234567890abcdef1234567890",
  "apiToken": "cf-api-token-here",
  "description": "Embeddings for document search"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/integrations/vectorize/indexes/create")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```