> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://respan.ai/docs/apis/spans/create-spans-in-bulk/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/_mcp/server.

# Create spans in bulk

POST https://api.respan.ai/api/request-logs/bulk/
Content-Type: application/json

Accepts up to 500 spans per request. Each item in `logs` uses the fields in [Create a span](/docs/apis/spans/create-span). Rows are processed independently. A `201 Created` response means at least one row was accepted, so check `error_count` and `errors` for partial failures. `success_count` counts rows that passed synchronous validation and were accepted for ingestion.

Rate limit: 30 requests per minute per organization for API-key calls, shared across the organization's keys. For JWT calls, the limit is per user. Metadata keys beginning with `_` are reserved for platform use and omitted from span and trace read responses.

Reference: https://respan.ai/docs/apis/spans/create-spans-in-bulk

## Authentication

- `Authorization` header (bearer token, required) — Use your Respan API key for Respan API authentication. Enter only the Respan API key value; clients send Authorization: Bearer \<RESPAN\_API\_KEY>. For /api/responses, provider credentials such as Perplexity, OpenAI, or Azure OpenAI go in Settings -> Providers or respan\_params.credential\_override in the request body, not in this authentication field.
- `Authorization` header (bearer token, required) — Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.

## Request

### Body (application/json)

This endpoint expects an object.

- `logs` (list of SpanCreateRequest, required) — Non-empty array of span payloads. Each object uses the same schema as `POST /api/request-logs/`.

## Response

### 201

At least one row was accepted. This status is also used for partial success; inspect the response counts and indexed errors.

- `success_count` (integer, required) — Number of items successfully processed.
- `error_count` (integer, required) — Number of items that failed.
- `errors` (list of BulkItemError, required) — Item-level failures, keyed by zero-based input index.

## Errors

### 400 Bad Request Error

Every row failed, the `logs` envelope was missing or malformed, the list was empty, or the organization is blocked.

- `BulkCreateSpansRequestBadRequestError`

### 403 Forbidden Error

The API key is missing, invalid or expired, or it can't access this organization.

- `detail` (string, required)

### 422 Unprocessable Entity Error

The batch contains more than 500 rows.

- `detail` (string, required)

### 429 Too Many Requests Error

Rate limit exceeded.

- `detail` (string, optional)

## Types

### SpanCreateRequest

Typed metadata that preserves native JSON types.

### BulkItemError

An item that failed during a bulk operation. `index` is zero-based and identifies the corresponding item in the request array.

- `index` (integer, required) — Zero-based index of the failed item in the submitted array.
- `error` (string, required) — Error message for the failed item.

### BulkOperationResponse

Canonical result envelope for a bulk operation.

- `success_count` (integer, required) — Number of items successfully processed.
- `error_count` (integer, required) — Number of items that failed.
- `errors` (list of BulkItemError, required) — Item-level failures, keyed by zero-based input index.

## Examples

### All rows accepted

**Request**

```json
{
  "logs": [
    {
      "model": "gpt-4o-mini",
      "prompt_messages": [
        {
          "role": "user",
          "content": "What is 2 + 2?"
        }
      ],
      "completion_message": {
        "role": "assistant",
        "content": "4"
      },
      "metadata": {
        "source": "lambda-batch"
      }
    },
    {
      "model": "gpt-4o-mini",
      "prompt_messages": [
        {
          "role": "user",
          "content": "What is the capital of France?"
        }
      ],
      "completion_message": {
        "role": "assistant",
        "content": "Paris"
      },
      "metadata": {
        "source": "lambda-batch"
      }
    }
  ]
}
```

**Response**

```json
{
  "success_count": 2,
  "error_count": 0,
  "errors": []
}
```

**SDK Code**

```python All rows accepted
import requests

url = "https://api.respan.ai/api/request-logs/bulk/"

payload = { "logs": [
        {
            "model": "gpt-4o-mini",
            "prompt_messages": [
                {
                    "role": "user",
                    "content": "What is 2 + 2?"
                }
            ],
            "completion_message": {
                "role": "assistant",
                "content": "4"
            },
            "metadata": { "source": "lambda-batch" }
        },
        {
            "model": "gpt-4o-mini",
            "prompt_messages": [
                {
                    "role": "user",
                    "content": "What is the capital of France?"
                }
            ],
            "completion_message": {
                "role": "assistant",
                "content": "Paris"
            },
            "metadata": { "source": "lambda-batch" }
        }
    ] }
headers = {
    "Authorization": "Bearer <respanApiKey>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript All rows accepted
const url = 'https://api.respan.ai/api/request-logs/bulk/';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <respanApiKey>', 'Content-Type': 'application/json'},
  body: '{"logs":[{"model":"gpt-4o-mini","prompt_messages":[{"role":"user","content":"What is 2 + 2?"}],"completion_message":{"role":"assistant","content":"4"},"metadata":{"source":"lambda-batch"}},{"model":"gpt-4o-mini","prompt_messages":[{"role":"user","content":"What is the capital of France?"}],"completion_message":{"role":"assistant","content":"Paris"},"metadata":{"source":"lambda-batch"}}]}'
};

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

```go All rows accepted
package main

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

func main() {

	url := "https://api.respan.ai/api/request-logs/bulk/"

	payload := strings.NewReader("{\n  \"logs\": [\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is 2 + 2?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"4\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    },\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is the capital of France?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Paris\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    }\n  ]\n}")

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

	req.Header.Add("Authorization", "Bearer <respanApiKey>")
	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 All rows accepted
require 'uri'
require 'net/http'

url = URI("https://api.respan.ai/api/request-logs/bulk/")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <respanApiKey>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"logs\": [\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is 2 + 2?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"4\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    },\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is the capital of France?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Paris\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    }\n  ]\n}"

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

```java All rows accepted
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.respan.ai/api/request-logs/bulk/")
  .header("Authorization", "Bearer <respanApiKey>")
  .header("Content-Type", "application/json")
  .body("{\n  \"logs\": [\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is 2 + 2?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"4\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    },\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is the capital of France?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Paris\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    }\n  ]\n}")
  .asString();
```

```php All rows accepted
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.respan.ai/api/request-logs/bulk/', [
  'body' => '{
  "logs": [
    {
      "model": "gpt-4o-mini",
      "prompt_messages": [
        {
          "role": "user",
          "content": "What is 2 + 2?"
        }
      ],
      "completion_message": {
        "role": "assistant",
        "content": "4"
      },
      "metadata": {
        "source": "lambda-batch"
      }
    },
    {
      "model": "gpt-4o-mini",
      "prompt_messages": [
        {
          "role": "user",
          "content": "What is the capital of France?"
        }
      ],
      "completion_message": {
        "role": "assistant",
        "content": "Paris"
      },
      "metadata": {
        "source": "lambda-batch"
      }
    }
  ]
}',
  'headers' => [
    'Authorization' => 'Bearer <respanApiKey>',
    'Content-Type' => 'application/json',
  ],
]);

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

```csharp All rows accepted
using RestSharp;

var client = new RestClient("https://api.respan.ai/api/request-logs/bulk/");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <respanApiKey>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"logs\": [\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is 2 + 2?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"4\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    },\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is the capital of France?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Paris\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    }\n  ]\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift All rows accepted
import Foundation

let headers = [
  "Authorization": "Bearer <respanApiKey>",
  "Content-Type": "application/json"
]
let parameters = ["logs": [
    [
      "model": "gpt-4o-mini",
      "prompt_messages": [
        [
          "role": "user",
          "content": "What is 2 + 2?"
        ]
      ],
      "completion_message": [
        "role": "assistant",
        "content": "4"
      ],
      "metadata": ["source": "lambda-batch"]
    ],
    [
      "model": "gpt-4o-mini",
      "prompt_messages": [
        [
          "role": "user",
          "content": "What is the capital of France?"
        ]
      ],
      "completion_message": [
        "role": "assistant",
        "content": "Paris"
      ],
      "metadata": ["source": "lambda-batch"]
    ]
  ]] as [String : Any]

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

let request = NSMutableURLRequest(url: NSURL(string: "https://api.respan.ai/api/request-logs/bulk/")! 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()
```

### One row rejected

**Request**

```json
{
  "logs": [
    {
      "model": "gpt-4o-mini",
      "prompt_messages": [
        {
          "role": "user",
          "content": "What is 2 + 2?"
        }
      ],
      "completion_message": {
        "role": "assistant",
        "content": "4"
      },
      "metadata": {
        "source": "lambda-batch"
      }
    },
    {
      "model": "gpt-4o-mini",
      "prompt_messages": [
        {}
      ]
    }
  ]
}
```

**Response**

```json
{
  "success_count": 1,
  "error_count": 1,
  "errors": [
    {
      "index": 1,
      "error": "Invalid logging format: Field required"
    }
  ]
}
```

**SDK Code**

```python One row rejected
import requests

url = "https://api.respan.ai/api/request-logs/bulk/"

payload = { "logs": [
        {
            "model": "gpt-4o-mini",
            "prompt_messages": [
                {
                    "role": "user",
                    "content": "What is 2 + 2?"
                }
            ],
            "completion_message": {
                "role": "assistant",
                "content": "4"
            },
            "metadata": { "source": "lambda-batch" }
        },
        {
            "model": "gpt-4o-mini",
            "prompt_messages": [{}]
        }
    ] }
headers = {
    "Authorization": "Bearer <respanApiKey>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript One row rejected
const url = 'https://api.respan.ai/api/request-logs/bulk/';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <respanApiKey>', 'Content-Type': 'application/json'},
  body: '{"logs":[{"model":"gpt-4o-mini","prompt_messages":[{"role":"user","content":"What is 2 + 2?"}],"completion_message":{"role":"assistant","content":"4"},"metadata":{"source":"lambda-batch"}},{"model":"gpt-4o-mini","prompt_messages":[{}]}]}'
};

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

```go One row rejected
package main

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

func main() {

	url := "https://api.respan.ai/api/request-logs/bulk/"

	payload := strings.NewReader("{\n  \"logs\": [\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is 2 + 2?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"4\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    },\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {}\n      ]\n    }\n  ]\n}")

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

	req.Header.Add("Authorization", "Bearer <respanApiKey>")
	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 One row rejected
require 'uri'
require 'net/http'

url = URI("https://api.respan.ai/api/request-logs/bulk/")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <respanApiKey>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"logs\": [\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is 2 + 2?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"4\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    },\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {}\n      ]\n    }\n  ]\n}"

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

```java One row rejected
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.respan.ai/api/request-logs/bulk/")
  .header("Authorization", "Bearer <respanApiKey>")
  .header("Content-Type", "application/json")
  .body("{\n  \"logs\": [\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is 2 + 2?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"4\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    },\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {}\n      ]\n    }\n  ]\n}")
  .asString();
```

```php One row rejected
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.respan.ai/api/request-logs/bulk/', [
  'body' => '{
  "logs": [
    {
      "model": "gpt-4o-mini",
      "prompt_messages": [
        {
          "role": "user",
          "content": "What is 2 + 2?"
        }
      ],
      "completion_message": {
        "role": "assistant",
        "content": "4"
      },
      "metadata": {
        "source": "lambda-batch"
      }
    },
    {
      "model": "gpt-4o-mini",
      "prompt_messages": [
        {}
      ]
    }
  ]
}',
  'headers' => [
    'Authorization' => 'Bearer <respanApiKey>',
    'Content-Type' => 'application/json',
  ],
]);

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

```csharp One row rejected
using RestSharp;

var client = new RestClient("https://api.respan.ai/api/request-logs/bulk/");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <respanApiKey>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"logs\": [\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"What is 2 + 2?\"\n        }\n      ],\n      \"completion_message\": {\n        \"role\": \"assistant\",\n        \"content\": \"4\"\n      },\n      \"metadata\": {\n        \"source\": \"lambda-batch\"\n      }\n    },\n    {\n      \"model\": \"gpt-4o-mini\",\n      \"prompt_messages\": [\n        {}\n      ]\n    }\n  ]\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift One row rejected
import Foundation

let headers = [
  "Authorization": "Bearer <respanApiKey>",
  "Content-Type": "application/json"
]
let parameters = ["logs": [
    [
      "model": "gpt-4o-mini",
      "prompt_messages": [
        [
          "role": "user",
          "content": "What is 2 + 2?"
        ]
      ],
      "completion_message": [
        "role": "assistant",
        "content": "4"
      ],
      "metadata": ["source": "lambda-batch"]
    ],
    [
      "model": "gpt-4o-mini",
      "prompt_messages": [[]]
    ]
  ]] as [String : Any]

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

let request = NSMutableURLRequest(url: NSURL(string: "https://api.respan.ai/api/request-logs/bulk/")! 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()
```