Token calculator (chat v3)

Available in Classic and VPC

Calculate number of tokens in sentences entered in the HCX model via Chat Completions V3.

Request

This section describes the request format. The method and URI are as follows:

Request headers

The following describes the request headers.

Request path parameters

You can use the following path parameters with your request:

Request body

You can include the following data in the body of your request:

ChatMessage

The following describes ChatMessage.

content

The following describes content.

tools

The following describes tools.

toolCalls

The following describes toolCalls.

Request example

The request example is as follows:

When querying with image

The following is a sample request when querying by image.

curl --location --request POST 'https://clovastudio.stream.ntruss.com/v3/api-tools/chat-tokenize/{modelName}' \
--header 'Authorization: Bearer {API Key}' \
--header 'X-NCP-CLOVASTUDIO-REQUEST-ID: {Request ID}' \
--header 'Content-Type: application/json' \
--data '{
    "messages": [
        {
            "role": "system",
            "content": "- This is a friendly AI assistant."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "imageUrl": [
                        {
                            "url": "https://www.******.com/image_a1b1c1.png"
                        }
                    ]
                },
                {
                    "type": "text",
                    "text": "Please describe this photo."
                }
            ]
        },
        {
            "role": "assistant",
            "content": "The photo shows a young child feeding a sheep."
        }
    ]
}'

When querying with text

The following is a sample request when querying by text.

curl --location --request POST 'https://clovastudio.stream.ntruss.com/v3/api-tools/chat-tokenize/{modelName}' \
--header 'Authorization: Bearer {API Key}' \
--header 'X-NCP-CLOVASTUDIO-REQUEST-ID: {Request ID}' \
--header 'Content-Type: application/json' \
--data '{
	"messages":[
		{
			"content": "What will the weather be like in Seoul tomorrow?",
			"role":"user"
		}
	],
	"tools":[
		{
			"type":"function",
			"function":{
				"description": "Tool that can provide weather information",
				"name":"weather",
				"parameters":{
					"properties":{
						"location":{
							"description": "City names such as Seoul, Daejeon, and Busan",
							"type":"string"
						},
						"unit":{
							"enum":[
								"celsius",
								"fahrenheit"
							],
							"type":"string"
						},
						"date":{
							"description": "Date string in the format such as 2023-08-01. Date you want to know the weather for",
							"type":"string"
						}
					},
					"required":[
						"location"
					],
					"type":"object"
				}
			}
		},
		{
			"type":"function",
			"function":{
				"description": "Tool that recommends travel destinations",
				"name":"travel",
				"parameters":{
					"properties":{
						"location":{
							"description":"The city and state, e.g. San Francisco, CA",
							"type":"string"
						},
						"date":{
							"description": "Date string in the format such as \"2023-08-01~2023-09-01\". Travel date range",
							"type":"string"
						}
					},
					"required":[
						"location"
					],
					"type":"object"
				}
			}
		}
	],
    "toolChoice":"auto"
}'

When querying with Structured Outputs

The following is a sample request when querying with Structured Outputs.

curl --location --request POST 'https://clovastudio.stream.ntruss.com/v3/api-tools/chat-tokenize/{modelName}' \
--header 'Authorization: Bearer {API Key}' \
--header 'X-NCP-CLOVASTUDIO-REQUEST-ID: {Request ID}' \
--header 'Content-Type: application/json' \
--data '{
    "messages": [
        {
            "role": "system",
            "content": "- An AI assistant that responds to a predefined JSON schema format."
        },
        {
            "role": "user",
            "content":  "Today's high is 32 degrees, the low is 15 degrees, and there is a 30% chance of precipitation."
        }
    ],
    "responseFormat": {
        "type" : "json",
        "schema": {
            "type": "object",
            "properties": {
                "temp_high_c": {
                "type": "number",
                "description": "Highest temperature (Celsius)"
                },
                "temp_low_c": {
                    "type": "number",
                    "description": "Lowest temperature (Celsius)"
                },
                "precipitation_percent": {
                    "type": "number",
                    "description": "Precipitation probability (%)",
                    "minimum": 0,
                    "maximum": 100
                }
            },
            "required": [
                "temp_high_c",
                "temp_low_c",
                "precipitation_percent"
            ]
        }
    }
}'

Response

This section describes the response format.

Response body

The response body includes the following data:

ChatMessageCount

The following describes ChatMessageCount.

ToolCount

The following describes ToolCount.

ResponseFormatCount

The following describes ResponseFormatCount.

Response example

The response example is as follows:

Succeeded

The following is a sample response upon a successful call.

{
    "status": {
        "code": "20000",
        "message": "OK"
    },
    "result": {
        "messages": [
            {
                "role": "system",
                "content": {
                    "type": "text",
                    "text": "- This is a friendly AI assistant.",
                    "count": 16
                }
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "image_url",
                        "imageUrl": {
                            "url": "https://www.******.com/image_a1b1c1.png"
                        },
                        "count": 1478
                    },
                    {
                        "type": "text",
                        "text": "Please describe this photo.",
                        "count": 12
                    }
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {
                        "type": "text",
                        "text": "The photo shows a young child feeding a sheep.",
                        "count": 20
                    }
                ]
            }
        ]
    }
}

{
    "status": {
        "code": "20000",
        "message": "OK"
    },
    "result": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "What will the weather be like in Seoul tomorrow?",
                        "count": 12
                    }
                ]
            }
        ],
        "tools": {
            "count": 230
        }
    }
}

{
    "status": {
        "code": "20000",
        "message": "OK"
    },
    "result": {
        "messages": [
            {
                "role": "system",
                "content": [
                    {
                        "type": "text",
                        "text": "- An AI assistant that responds to a predefined JSON schema format.",
                        "count": 18
                    }
                ]
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "Today's high is 32 degrees, the low is 15 degrees, and there is a 30% chance of precipitation.",
                        "count": 27
                    }
                ]
            }
        ],
        "responseFormat": {
            "count": 86
        }
    }
}

Failure

The following is a sample response upon a failed call.

• Common client error troubleshooting (4xx)
• Common server error troubleshooting (5xx)