Creates a chat conversation.

curl --request POST \
  --url http://{device-ip}:{device-port}/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22"
          }
        }
      ]
    }
  ],
  "model": "qwen2.5-vl-3b",
  "frequency_penalty": 0,
  "max_completion_tokens": 123,
  "presence_penalty": 0,
  "safety_identifier": "<string>",
  "seed": 42,
  "stream": false,
  "temperature": 1,
  "top_p": 1,
  "top_k": 40
}
'

import requests

url = "http://{device-ip}:{device-port}/v1/chat/completions"

payload = {
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "What is in this image?"
                },
                {
                    "type": "image_url",
                    "image_url": { "url": "https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22" }
                }
            ]
        }
    ],
    "model": "qwen2.5-vl-3b",
    "frequency_penalty": 0,
    "max_completion_tokens": 123,
    "presence_penalty": 0,
    "safety_identifier": "<string>",
    "seed": 42,
    "stream": False,
    "temperature": 1,
    "top_p": 1,
    "top_k": 40
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    messages: [
      {role: 'system', content: 'You are a helpful assistant.'},
      {
        role: 'user',
        content: [
          {type: 'text', text: 'What is in this image?'},
          {
            type: 'image_url',
            image_url: {
              url: 'https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22'
            }
          }
        ]
      }
    ],
    model: 'qwen2.5-vl-3b',
    frequency_penalty: 0,
    max_completion_tokens: 123,
    presence_penalty: 0,
    safety_identifier: '<string>',
    seed: 42,
    stream: false,
    temperature: 1,
    top_p: 1,
    top_k: 40
  })
};

fetch('http://{device-ip}:{device-port}/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_PORT => "62437",
  CURLOPT_URL => "http://{device-ip}:{device-port}/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'messages' => [
        [
                'role' => 'system',
                'content' => 'You are a helpful assistant.'
        ],
        [
                'role' => 'user',
                'content' => [
                                [
                                                                'type' => 'text',
                                                                'text' => 'What is in this image?'
                                ],
                                [
                                                                'type' => 'image_url',
                                                                'image_url' => [
                                                                                                                                'url' => 'https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22'
                                                                ]
                                ]
                ]
        ]
    ],
    'model' => 'qwen2.5-vl-3b',
    'frequency_penalty' => 0,
    'max_completion_tokens' => 123,
    'presence_penalty' => 0,
    'safety_identifier' => '<string>',
    'seed' => 42,
    'stream' => false,
    'temperature' => 1,
    'top_p' => 1,
    'top_k' => 40
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "http://{device-ip}:{device-port}/v1/chat/completions"

	payload := strings.NewReader("{\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"What is in this image?\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22\"\n          }\n        }\n      ]\n    }\n  ],\n  \"model\": \"qwen2.5-vl-3b\",\n  \"frequency_penalty\": 0,\n  \"max_completion_tokens\": 123,\n  \"presence_penalty\": 0,\n  \"safety_identifier\": \"<string>\",\n  \"seed\": 42,\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"top_k\": 40\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(string(body))

}

HttpResponse<String> response = Unirest.post("http://{device-ip}:{device-port}/v1/chat/completions")
  .header("Content-Type", "application/json")
  .body("{\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"What is in this image?\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22\"\n          }\n        }\n      ]\n    }\n  ],\n  \"model\": \"qwen2.5-vl-3b\",\n  \"frequency_penalty\": 0,\n  \"max_completion_tokens\": 123,\n  \"presence_penalty\": 0,\n  \"safety_identifier\": \"<string>\",\n  \"seed\": 42,\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"top_k\": 40\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("http://{device-ip}:{device-port}/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"What is in this image?\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22\"\n          }\n        }\n      ]\n    }\n  ],\n  \"model\": \"qwen2.5-vl-3b\",\n  \"frequency_penalty\": 0,\n  \"max_completion_tokens\": 123,\n  \"presence_penalty\": 0,\n  \"safety_identifier\": \"<string>\",\n  \"seed\": 42,\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"top_k\": 40\n}"

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

{
  "id": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "content": "<string>",
        "role": "assistant",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      }
    }
  ],
  "created": 123,
  "object": "chat.completion",
  "model": "<string>",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  }
}

POST

chat

completions

Creates a chat conversation.

curl --request POST \
  --url http://{device-ip}:{device-port}/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22"
          }
        }
      ]
    }
  ],
  "model": "qwen2.5-vl-3b",
  "frequency_penalty": 0,
  "max_completion_tokens": 123,
  "presence_penalty": 0,
  "safety_identifier": "<string>",
  "seed": 42,
  "stream": false,
  "temperature": 1,
  "top_p": 1,
  "top_k": 40
}
'

import requests

url = "http://{device-ip}:{device-port}/v1/chat/completions"

payload = {
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "What is in this image?"
                },
                {
                    "type": "image_url",
                    "image_url": { "url": "https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22" }
                }
            ]
        }
    ],
    "model": "qwen2.5-vl-3b",
    "frequency_penalty": 0,
    "max_completion_tokens": 123,
    "presence_penalty": 0,
    "safety_identifier": "<string>",
    "seed": 42,
    "stream": False,
    "temperature": 1,
    "top_p": 1,
    "top_k": 40
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    messages: [
      {role: 'system', content: 'You are a helpful assistant.'},
      {
        role: 'user',
        content: [
          {type: 'text', text: 'What is in this image?'},
          {
            type: 'image_url',
            image_url: {
              url: 'https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22'
            }
          }
        ]
      }
    ],
    model: 'qwen2.5-vl-3b',
    frequency_penalty: 0,
    max_completion_tokens: 123,
    presence_penalty: 0,
    safety_identifier: '<string>',
    seed: 42,
    stream: false,
    temperature: 1,
    top_p: 1,
    top_k: 40
  })
};

fetch('http://{device-ip}:{device-port}/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_PORT => "62437",
  CURLOPT_URL => "http://{device-ip}:{device-port}/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'messages' => [
        [
                'role' => 'system',
                'content' => 'You are a helpful assistant.'
        ],
        [
                'role' => 'user',
                'content' => [
                                [
                                                                'type' => 'text',
                                                                'text' => 'What is in this image?'
                                ],
                                [
                                                                'type' => 'image_url',
                                                                'image_url' => [
                                                                                                                                'url' => 'https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22'
                                                                ]
                                ]
                ]
        ]
    ],
    'model' => 'qwen2.5-vl-3b',
    'frequency_penalty' => 0,
    'max_completion_tokens' => 123,
    'presence_penalty' => 0,
    'safety_identifier' => '<string>',
    'seed' => 42,
    'stream' => false,
    'temperature' => 1,
    'top_p' => 1,
    'top_k' => 40
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "http://{device-ip}:{device-port}/v1/chat/completions"

	payload := strings.NewReader("{\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"What is in this image?\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22\"\n          }\n        }\n      ]\n    }\n  ],\n  \"model\": \"qwen2.5-vl-3b\",\n  \"frequency_penalty\": 0,\n  \"max_completion_tokens\": 123,\n  \"presence_penalty\": 0,\n  \"safety_identifier\": \"<string>\",\n  \"seed\": 42,\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"top_k\": 40\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(string(body))

}

HttpResponse<String> response = Unirest.post("http://{device-ip}:{device-port}/v1/chat/completions")
  .header("Content-Type", "application/json")
  .body("{\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"What is in this image?\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22\"\n          }\n        }\n      ]\n    }\n  ],\n  \"model\": \"qwen2.5-vl-3b\",\n  \"frequency_penalty\": 0,\n  \"max_completion_tokens\": 123,\n  \"presence_penalty\": 0,\n  \"safety_identifier\": \"<string>\",\n  \"seed\": 42,\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"top_k\": 40\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("http://{device-ip}:{device-port}/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"What is in this image?\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22\"\n          }\n        }\n      ]\n    }\n  ],\n  \"model\": \"qwen2.5-vl-3b\",\n  \"frequency_penalty\": 0,\n  \"max_completion_tokens\": 123,\n  \"presence_penalty\": 0,\n  \"safety_identifier\": \"<string>\",\n  \"seed\": 42,\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 1,\n  \"top_k\": 40\n}"

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

{
  "id": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "content": "<string>",
        "role": "assistant",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      }
    }
  ],
  "created": 123,
  "object": "chat.completion",
  "model": "<string>",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  }
}

Body

application/json

messages

(System message · object | User message · object | Assistant message · object | Tool message · object)[]

required

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

Minimum array length: 1

System message
User message
Assistant message
Tool message

Show child attributes

Example:

[
  {
    "role": "system",
    "content": "You are a helpful assistant."
  },
  {
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": "What is in this image?"
      },
      {
        "type": "image_url",
        "image_url": {
          "url": "https://images.pexels.com/photos/210186/pexels-photo-210186.jpeg?cs=srgb&dl=cascade-clouds-cool-wallpaper-210186.jpg&fm=jpg%22"
        }
      }
    ]
  }
]

model

string

required

Model ID used to generate the response.

Example:

"qwen2.5-vl-3b"

frequency_penalty

number | null

default:0

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

Required range: -2 <= x <= 2

max_completion_tokens

integer | null

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

presence_penalty

number | null

default:0

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

Required range: -2 <= x <= 2

safety_identifier

string | null

A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user.

seed

integer | null

If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

Required range: -9223372036854776000 <= x <= 9223372036854776000

Example:

42

stream

boolean | null

default:false

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

temperature

number | null

default:1

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

Required range: 0 <= x <= 2

top_p

number | null

default:1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

Required range: 0 <= x <= 1

top_k

integer | null

default:40

Top-k sampling parameter. If specified, the sampler considers only the k most likely next tokens at each step. If omitted, the model's configured sampler defaults are used.

Required range: x >= 1

Response

200 - application/json

Represents a chat completion response returned by model, based on the provided input.

string

required

A unique identifier for the chat completion.

choices

object[]

required

A list of chat completion choices. Can be more than one if n is greater than 1.

Show child attributes

created

integer

required

The Unix timestamp (in seconds) of when the chat completion was created.

object

enum<string>

required

The object type, which is always chat.completion.

Available options:

chat.completion

model

string

The model used for the chat completion.

usage

object

Usage statistics for the completion request.

Show child attributes

Running on a specific NPU (QCS9075)Delete a stored chat completion