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

# Update, commit, or deploy prompts in bulk

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

Process 1 to 100 prompt operations sequentially in request order using exact `prompt_id` matching. Each item runs in its own transaction, so a failed item is rolled back without undoing successful items. `update` changes model configuration on the latest draft and does not accept content fields such as `messages`, `variables`, or `description`; `commit` snapshots the latest draft; `deploy` promotes the latest committed version. A later duplicate successful `commit` or `deploy` for the same prompt in one request is returned as an indexed error. This endpoint inherits the caller's configured API-key or JWT rate limits; it has no fixed endpoint-specific RPM.

Reference: https://respan.ai/docs/apis/prompts/update-commit-or-deploy-prompts-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 a PromptBulkRequest.

- `requests` (list of PromptBulkRequestItem, required) — Prompt operations. Error indices refer to this zero-based array.

## Response

### 200

All prompt operations succeeded.

- `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.

### 207

Some prompt operations succeeded and some failed. Successful items remain committed.

- `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

The request failed validation, or every prompt operation failed.

- `ProcessPromptBulkOperationsRequestBadRequestError`

### 403 Forbidden Error

The API key is missing, invalid or expired, or it can't update prompts.

- `detail` (string, required)

### 422 Unprocessable Entity Error

The request contains more than 100 prompt operations.

- `detail` (string, required)

### 429 Too Many Requests Error

Rate limit exceeded.

- `detail` (string, required)
- `retry_after` (integer, optional) — Seconds to wait before retrying, when provided.

## Types

### PromptBulkRequestItem

One action in a prompt bulk request.

- `action`: `update` (update)
  - `body` (PromptBulkUpdateBody, required) — Non-empty model configuration changes for the latest draft. Prompt content fields are not accepted.
  - `prompt_id` (string, required) — Exact prompt ID to mutate.
- `action`: `commit` (commit)
  - `prompt_id` (string, required) — Exact prompt ID to mutate.
  - `body` (PromptBulkCommitBody, optional) — Optional commit metadata.
- `action`: `deploy` (deploy)
  - `prompt_id` (string, required) — Exact prompt ID to mutate.
  - `body` (PromptBulkRequestItemDiscriminatorMappingDeployBody, optional) — If provided, this object must be empty.

### 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.

### ProcessPromptBulkOperationsRequestBadRequestError1

- `requests` (list of any, required) — DRF validation errors for the request array.

### PromptBulkUpdateBody

Non-empty model configuration changes for the latest draft. Prompt content fields are not accepted.

- `model` (string, optional) — Primary model for the draft.
- `stream` (boolean, optional) — Whether gateway responses using this prompt should stream.
- `temperature` (double, optional, nullable) — Sampling temperature.
- `max_tokens` (integer, optional, nullable) — Maximum output tokens.
- `top_p` (double, optional, nullable) — Nucleus-sampling probability mass.
- `frequency_penalty` (double, optional, nullable) — Frequency penalty.
- `presence_penalty` (double, optional, nullable) — Presence penalty.
- `reasoning_effort` (string, optional, nullable) — Provider-specific reasoning effort.
- `verbosity` (string, optional, nullable) — Provider-specific output verbosity.
- `thinking` (any, optional) — Provider-specific thinking configuration. Any JSON value is accepted.
- `seed` (integer, optional, nullable) — Optional deterministic sampling seed.
- `fallback_models` (list of string, optional, nullable) — Fallback model identifiers.
- `load_balance_models` (list of any, optional, nullable) — Load-balancing model configurations.
- `tools` (list of any, optional, nullable) — Tool definitions made available to the model.
- `tool_choice` (any, optional) — Tool-selection configuration. Any JSON value is accepted.
- `response_format` (any, optional) — Structured response-format configuration. Any JSON value is accepted.
- `json_schema` (any, optional) — JSON schema for structured output. Any JSON value is accepted.
- `is_enforcing_response_format` (boolean, optional) — Whether to enforce the configured response format.

### PromptBulkCommitBody

Optional commit metadata.

- `description` (string, optional) — Optional commit message. Blank strings are accepted.

### PromptBulkRequestItemDiscriminatorMappingDeployBody

If provided, this object must be empty.

## Examples

**Request**

```json
{
  "requests": [
    {
      "action": "update",
      "body": {
        "model": "gpt-4o-mini",
        "temperature": 0.25,
        "max_tokens": 512
      },
      "prompt_id": "prm_customer_support"
    },
    {
      "action": "commit",
      "prompt_id": "prm_customer_support",
      "body": {
        "description": "Tune production configuration"
      }
    },
    {
      "action": "deploy",
      "prompt_id": "prm_customer_support"
    }
  ]
}
```

**Response**

```json
{
  "success_count": 3,
  "error_count": 0,
  "errors": []
}
```

**SDK Code**

```python
import requests

url = "https://api.respan.ai/api/prompts/bulk/"

payload = { "requests": [
        {
            "action": "update",
            "body": {
                "model": "gpt-4o-mini",
                "temperature": 0.25,
                "max_tokens": 512
            },
            "prompt_id": "prm_customer_support"
        },
        {
            "action": "commit",
            "prompt_id": "prm_customer_support",
            "body": { "description": "Tune production configuration" }
        },
        {
            "action": "deploy",
            "prompt_id": "prm_customer_support"
        }
    ] }
headers = {
    "Authorization": "Bearer <respanApiKey>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript
const url = 'https://api.respan.ai/api/prompts/bulk/';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <respanApiKey>', 'Content-Type': 'application/json'},
  body: '{"requests":[{"action":"update","body":{"model":"gpt-4o-mini","temperature":0.25,"max_tokens":512},"prompt_id":"prm_customer_support"},{"action":"commit","prompt_id":"prm_customer_support","body":{"description":"Tune production configuration"}},{"action":"deploy","prompt_id":"prm_customer_support"}]}'
};

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

```go
package main

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

func main() {

	url := "https://api.respan.ai/api/prompts/bulk/"

	payload := strings.NewReader("{\n  \"requests\": [\n    {\n      \"action\": \"update\",\n      \"body\": {\n        \"model\": \"gpt-4o-mini\",\n        \"temperature\": 0.25,\n        \"max_tokens\": 512\n      },\n      \"prompt_id\": \"prm_customer_support\"\n    },\n    {\n      \"action\": \"commit\",\n      \"prompt_id\": \"prm_customer_support\",\n      \"body\": {\n        \"description\": \"Tune production configuration\"\n      }\n    },\n    {\n      \"action\": \"deploy\",\n      \"prompt_id\": \"prm_customer_support\"\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
require 'uri'
require 'net/http'

url = URI("https://api.respan.ai/api/prompts/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  \"requests\": [\n    {\n      \"action\": \"update\",\n      \"body\": {\n        \"model\": \"gpt-4o-mini\",\n        \"temperature\": 0.25,\n        \"max_tokens\": 512\n      },\n      \"prompt_id\": \"prm_customer_support\"\n    },\n    {\n      \"action\": \"commit\",\n      \"prompt_id\": \"prm_customer_support\",\n      \"body\": {\n        \"description\": \"Tune production configuration\"\n      }\n    },\n    {\n      \"action\": \"deploy\",\n      \"prompt_id\": \"prm_customer_support\"\n    }\n  ]\n}"

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

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.respan.ai/api/prompts/bulk/")
  .header("Authorization", "Bearer <respanApiKey>")
  .header("Content-Type", "application/json")
  .body("{\n  \"requests\": [\n    {\n      \"action\": \"update\",\n      \"body\": {\n        \"model\": \"gpt-4o-mini\",\n        \"temperature\": 0.25,\n        \"max_tokens\": 512\n      },\n      \"prompt_id\": \"prm_customer_support\"\n    },\n    {\n      \"action\": \"commit\",\n      \"prompt_id\": \"prm_customer_support\",\n      \"body\": {\n        \"description\": \"Tune production configuration\"\n      }\n    },\n    {\n      \"action\": \"deploy\",\n      \"prompt_id\": \"prm_customer_support\"\n    }\n  ]\n}")
  .asString();
```

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

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.respan.ai/api/prompts/bulk/', [
  'body' => '{
  "requests": [
    {
      "action": "update",
      "body": {
        "model": "gpt-4o-mini",
        "temperature": 0.25,
        "max_tokens": 512
      },
      "prompt_id": "prm_customer_support"
    },
    {
      "action": "commit",
      "prompt_id": "prm_customer_support",
      "body": {
        "description": "Tune production configuration"
      }
    },
    {
      "action": "deploy",
      "prompt_id": "prm_customer_support"
    }
  ]
}',
  'headers' => [
    'Authorization' => 'Bearer <respanApiKey>',
    'Content-Type' => 'application/json',
  ],
]);

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

```csharp
using RestSharp;

var client = new RestClient("https://api.respan.ai/api/prompts/bulk/");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <respanApiKey>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"requests\": [\n    {\n      \"action\": \"update\",\n      \"body\": {\n        \"model\": \"gpt-4o-mini\",\n        \"temperature\": 0.25,\n        \"max_tokens\": 512\n      },\n      \"prompt_id\": \"prm_customer_support\"\n    },\n    {\n      \"action\": \"commit\",\n      \"prompt_id\": \"prm_customer_support\",\n      \"body\": {\n        \"description\": \"Tune production configuration\"\n      }\n    },\n    {\n      \"action\": \"deploy\",\n      \"prompt_id\": \"prm_customer_support\"\n    }\n  ]\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = [
  "Authorization": "Bearer <respanApiKey>",
  "Content-Type": "application/json"
]
let parameters = ["requests": [
    [
      "action": "update",
      "body": [
        "model": "gpt-4o-mini",
        "temperature": 0.25,
        "max_tokens": 512
      ],
      "prompt_id": "prm_customer_support"
    ],
    [
      "action": "commit",
      "prompt_id": "prm_customer_support",
      "body": ["description": "Tune production configuration"]
    ],
    [
      "action": "deploy",
      "prompt_id": "prm_customer_support"
    ]
  ]] as [String : Any]

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

let request = NSMutableURLRequest(url: NSURL(string: "https://api.respan.ai/api/prompts/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()
```