> This page is for version 1.14.0 (default).
> For other versions, use one of these documentation indexes:
> - 1.14.0 (default): https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.14.0/llms.txt
> - 1.10.1: https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/_mcp/server.

# LlamaStack-compatible completion endpoint

POST /experimental/ls/inference/completion
Content-Type: application/json

Reference: https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/api-reference/create-llama-stack-completion-experimental-ls-inference-completion-post

## Request

### Body (application/json)

This endpoint expects a CompletionRequest.

- `model` (string, required)
- `content` (CompletionRequestContent, required)
- `sampling_params` (SamplingParams, optional, nullable, default: {"max_tokens":0,"repetition_penalty":1,"strategy":"greedy","temperature":0,"top_k":0,"top_p":0.95})
- `stream` (boolean, optional, nullable, default: false)
- `logprobs` (LogProbConfig, optional, nullable)

## Response

### 200

Successful Response

- `create_llama_stack_completion_experimental_ls_inference_completion_post_Response_200`
  - CompletionResponse: nim_llm_sdk__entrypoints__llamastack__protocol__CompletionResponse
  - CompletionResponseStreamChunk: CompletionResponseStreamChunk

## Errors

### 400 Bad Request Error

Received an invalid request possibly containing unsupported or out-of-range parameter values.

- `message` (string, required)
- `type` (string, required)
- `code` (integer, required)
- `object` (string, optional, default: error)
- `param` (string, optional, nullable)

### 404 Not Found Error

The requested model does not exist.

- `message` (string, required)
- `type` (string, required)
- `code` (integer, required)
- `object` (string, optional, default: error)
- `param` (string, optional, nullable)

### 415 Unsupported Media Type Error

Unsupported Media Type

- `message` (string, required)
- `type` (string, required)
- `code` (integer, required)
- `object` (string, optional, default: error)
- `param` (string, optional, nullable)

### 422 Unprocessable Entity Error

Validation Error

- `detail` (list of ValidationError, optional)

### 500 Internal Server Error

Internal Server Error

- `message` (string, required)
- `type` (string, required)
- `code` (integer, required)
- `object` (string, optional, default: error)
- `param` (string, optional, nullable)

## Types

### CompletionRequestContent

- string
- Attachment: Attachment
- list of CompletionRequestContentOneOf2Items

### SamplingParams

- `strategy` (enum, optional)
  - Allowed values: `greedy`, `top_p`, `top_k`
- `temperature` (double, optional, nullable, default: 0)
- `top_p` (double, optional, nullable, default: 0.95)
- `top_k` (integer, optional, nullable, default: 0)
- `max_tokens` (integer, optional, nullable, default: 0)
- `repetition_penalty` (double, optional, nullable, default: 1)

### LogProbConfig

- `top_k` (integer, optional, nullable, default: 0)

### nim_llm_sdk__entrypoints__llamastack__protocol__CompletionResponse

- `completion_message` (CompletionMessage-Output, required)
- `logprobs` (list of TokenLogProbs, optional, nullable)

### CompletionResponseStreamChunk

streamed completion response.

- `delta` (string, required)
- `stop_reason` (enum, optional, nullable)
  - Allowed values: `end_of_turn`, `end_of_message`, `out_of_tokens`
- `logprobs` (list of TokenLogProbs, optional, nullable)

### ValidationError

- `loc` (list of ValidationErrorLocItems, required)
- `msg` (string, required)
- `type` (string, required)

### Attachment

- `url` (URL, required)
- `mime_type` (string, required)

### CompletionRequestContentOneOf2Items

- string
- Attachment: Attachment

### CompletionMessage-Output

- `content` (CompletionMessageOutputContent, required)
- `stop_reason` (enum, required)
  - Allowed values: `end_of_turn`, `end_of_message`, `out_of_tokens`
- `role` ("assistant", optional, default: assistant)
- `tool_calls` (list of nim_llm_sdk__entrypoints__llamastack__protocol__ToolCall, optional)

### TokenLogProbs

- `logprobs_by_token` (map from string to double, required)

### ValidationErrorLocItems

- string
- integer

### URL

- `uri` (string, required)

### CompletionMessageOutputContent

- string
- Attachment: Attachment
- list of CompletionMessageOutputContentOneOf2Items

### nim_llm_sdk__entrypoints__llamastack__protocol__ToolCall

- `tool_name` (NimLlmSdkEntrypointsLlamastackProtocolToolCallToolName, required)
- `call_id` (string, optional)
- `arguments` (map from string to NimLlmSdkEntrypointsLlamastackProtocolToolCallArguments, optional, nullable)

### CompletionMessageOutputContentOneOf2Items

- string
- Attachment: Attachment

### NimLlmSdkEntrypointsLlamastackProtocolToolCallToolName

- BuiltinTool: enum
  - Allowed values: `brave_search`, `wolfram_alpha`, `photogen`, `code_interpreter`
- string

### NimLlmSdkEntrypointsLlamastackProtocolToolCallArguments

- string
- integer
- double
- boolean
- list of NimLlmSdkEntrypointsLlamastackProtocolToolCallArgumentsOneOf4Items
- map from string to NimLlmSdkEntrypointsLlamastackProtocolToolCallArgumentsOneOf5

### NimLlmSdkEntrypointsLlamastackProtocolToolCallArgumentsOneOf4Items

- string
- integer
- double
- boolean

### NimLlmSdkEntrypointsLlamastackProtocolToolCallArgumentsOneOf5

- string
- integer
- double
- boolean

## Examples

**Request**

```json
{
  "model": "string",
  "content": "string"
}
```

**Response**

```json
{
  "completion_message": {
    "content": "string",
    "role": "assistant",
    "stop_reason": "end_of_turn",
    "tool_calls": [
      {
        "arguments": {},
        "call_id": "string",
        "tool_name": "brave_search"
      }
    ]
  },
  "logprobs": [
    {
      "logprobs_by_token": {}
    }
  ]
}
```

**SDK Code**

```python
import requests

url = "https://api.example.com/experimental/ls/inference/completion"

payload = {
    "model": "string",
    "content": "string"
}
headers = {"Content-Type": "application/json"}

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

print(response.json())
```

```javascript
const url = 'https://api.example.com/experimental/ls/inference/completion';
const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: '{"model":"string","content":"string"}'
};

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.example.com/experimental/ls/inference/completion"

	payload := strings.NewReader("{\n  \"model\": \"string\",\n  \"content\": \"string\"\n}")

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

	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.example.com/experimental/ls/inference/completion")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"string\",\n  \"content\": \"string\"\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.example.com/experimental/ls/inference/completion")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"string\",\n  \"content\": \"string\"\n}")
  .asString();
```

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

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.example.com/experimental/ls/inference/completion', [
  'body' => '{
  "model": "string",
  "content": "string"
}',
  'headers' => [
    'Content-Type' => 'application/json',
  ],
]);

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

```csharp
using RestSharp;

var client = new RestClient("https://api.example.com/experimental/ls/inference/completion");
var request = new RestRequest(Method.POST);
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"string\",\n  \"content\": \"string\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = ["Content-Type": "application/json"]
let parameters = [
  "model": "string",
  "content": "string"
] as [String : Any]

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

let request = NSMutableURLRequest(url: NSURL(string: "https://api.example.com/experimental/ls/inference/completion")! 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()
```