Qwen Image

Chat Completions qwen ilm

curl --request POST \
  --url https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen:qwen3-vl-plus",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "top_p": 0.9,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "n": 1,
  "stream": false,
  "stop": "<string>",
  "extra_body": {
    "metadata": {
      "enable_thinking": true,
      "thinking_budget": 123,
      "response_format": {
        "type": "json_schema",
        "json_schema": {
          "name": "<string>",
          "schema": {
            "type": "object",
            "properties": {},
            "required": [
              "<string>"
            ]
          }
        }
      }
    }
  }
}
'

import requests

url = "https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions"

payload = {
    "model": "qwen:qwen3-vl-plus",
    "messages": [{ "content": "<string>" }],
    "temperature": 0.7,
    "max_tokens": 1024,
    "top_p": 0.9,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "n": 1,
    "stream": False,
    "stop": "<string>",
    "extra_body": { "metadata": {
            "enable_thinking": True,
            "thinking_budget": 123,
            "response_format": {
                "type": "json_schema",
                "json_schema": {
                    "name": "<string>",
                    "schema": {
                        "type": "object",
                        "properties": {},
                        "required": ["<string>"]
                    }
                }
            }
        } }
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'qwen:qwen3-vl-plus',
    messages: [{content: '<string>'}],
    temperature: 0.7,
    max_tokens: 1024,
    top_p: 0.9,
    frequency_penalty: 0,
    presence_penalty: 0,
    n: 1,
    stream: false,
    stop: '<string>',
    extra_body: {
      metadata: {
        enable_thinking: true,
        thinking_budget: 123,
        response_format: {
          type: 'json_schema',
          json_schema: {
            name: '<string>',
            schema: {type: 'object', properties: {}, required: ['<string>']}
          }
        }
      }
    }
  })
};

fetch('https://mavi-backend.memories.ai/serve/api/v2/iu/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_URL => "https://mavi-backend.memories.ai/serve/api/v2/iu/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([
    'model' => 'qwen:qwen3-vl-plus',
    'messages' => [
        [
                'content' => '<string>'
        ]
    ],
    'temperature' => 0.7,
    'max_tokens' => 1024,
    'top_p' => 0.9,
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'n' => 1,
    'stream' => false,
    'stop' => '<string>',
    'extra_body' => [
        'metadata' => [
                'enable_thinking' => true,
                'thinking_budget' => 123,
                'response_format' => [
                                'type' => 'json_schema',
                                'json_schema' => [
                                                                'name' => '<string>',
                                                                'schema' => [
                                                                                                                                'type' => 'object',
                                                                                                                                'properties' => [
                                                                                                                                                                                                                                                                
                                                                                                                                ],
                                                                                                                                'required' => [
                                                                                                                                                                                                                                                                '<string>'
                                                                                                                                ]
                                                                ]
                                ]
                ]
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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 := "https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"qwen:qwen3-vl-plus\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 0.7,\n  \"max_tokens\": 1024,\n  \"top_p\": 0.9,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"n\": 1,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"extra_body\": {\n    \"metadata\": {\n      \"enable_thinking\": true,\n      \"thinking_budget\": 123,\n      \"response_format\": {\n        \"type\": \"json_schema\",\n        \"json_schema\": {\n          \"name\": \"<string>\",\n          \"schema\": {\n            \"type\": \"object\",\n            \"properties\": {},\n            \"required\": [\n              \"<string>\"\n            ]\n          }\n        }\n      }\n    }\n  }\n}")

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

	req.Header.Add("Authorization", "<api-key>")
	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("https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"qwen:qwen3-vl-plus\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 0.7,\n  \"max_tokens\": 1024,\n  \"top_p\": 0.9,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"n\": 1,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"extra_body\": {\n    \"metadata\": {\n      \"enable_thinking\": true,\n      \"thinking_budget\": 123,\n      \"response_format\": {\n        \"type\": \"json_schema\",\n        \"json_schema\": {\n          \"name\": \"<string>\",\n          \"schema\": {\n            \"type\": \"object\",\n            \"properties\": {},\n            \"required\": [\n              \"<string>\"\n            ]\n          }\n        }\n      }\n    }\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"qwen:qwen3-vl-plus\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 0.7,\n  \"max_tokens\": 1024,\n  \"top_p\": 0.9,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"n\": 1,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"extra_body\": {\n    \"metadata\": {\n      \"enable_thinking\": true,\n      \"thinking_budget\": 123,\n      \"response_format\": {\n        \"type\": \"json_schema\",\n        \"json_schema\": {\n          \"name\": \"<string>\",\n          \"schema\": {\n            \"type\": \"object\",\n            \"properties\": {},\n            \"required\": [\n              \"<string>\"\n            ]\n          }\n        }\n      }\n    }\n  }\n}"

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

{
  "id": "6612267a-d08f-9ea0-a254-7bcea6339f49",
  "object": "completion",
  "model": "qwen3-vl-plus",
  "created_at": 1767094289,
  "status": "completed",
  "choices": [
    {
      "text": "This image is from the game Half-Life 2, showing a game scene from a first-person perspective.\n\nIn the scene, the player holds a \"Gravity Gun\" in each hand, aiming at the wall ahead. A yellow \"Mandatory Reminder\" sign hangs on the wall, printed with the U.S. national emblem pattern and inscribed with \"AMENDMENT 35\" (35th Amendment), with text below reading: \"No person shall be found with fewer than thirteen times their own body weight of federally provisioned munitions.\" - This is clearly a fictional absurd law within the game.\n\nThe bottom left corner of the screen shows the player's \"HEALTH\" and \"SUIT\" both at 100. The bottom right corner displays ammunition information \"IDC ANYMORE AMMO\", suggesting ample or infinite ammunition.\n\nThe entire scene is full of dark humor and dystopian style, one of the iconic scenes from Half-Life 2, often used by players as memes or screenshots for sharing.",
      "index": 0
    }
  ],
  "usage": {
    "input_tokens": 235,
    "output_tokens": 229,
    "total_tokens": 464
  },
  "meta": {
    "provider": "qwen",
    "provider_model": "qwen3-vl-plus"
  }
}

POST

chat

completions

Chat Completions qwen ilm

curl --request POST \
  --url https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen:qwen3-vl-plus",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "top_p": 0.9,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "n": 1,
  "stream": false,
  "stop": "<string>",
  "extra_body": {
    "metadata": {
      "enable_thinking": true,
      "thinking_budget": 123,
      "response_format": {
        "type": "json_schema",
        "json_schema": {
          "name": "<string>",
          "schema": {
            "type": "object",
            "properties": {},
            "required": [
              "<string>"
            ]
          }
        }
      }
    }
  }
}
'

import requests

url = "https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions"

payload = {
    "model": "qwen:qwen3-vl-plus",
    "messages": [{ "content": "<string>" }],
    "temperature": 0.7,
    "max_tokens": 1024,
    "top_p": 0.9,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "n": 1,
    "stream": False,
    "stop": "<string>",
    "extra_body": { "metadata": {
            "enable_thinking": True,
            "thinking_budget": 123,
            "response_format": {
                "type": "json_schema",
                "json_schema": {
                    "name": "<string>",
                    "schema": {
                        "type": "object",
                        "properties": {},
                        "required": ["<string>"]
                    }
                }
            }
        } }
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'qwen:qwen3-vl-plus',
    messages: [{content: '<string>'}],
    temperature: 0.7,
    max_tokens: 1024,
    top_p: 0.9,
    frequency_penalty: 0,
    presence_penalty: 0,
    n: 1,
    stream: false,
    stop: '<string>',
    extra_body: {
      metadata: {
        enable_thinking: true,
        thinking_budget: 123,
        response_format: {
          type: 'json_schema',
          json_schema: {
            name: '<string>',
            schema: {type: 'object', properties: {}, required: ['<string>']}
          }
        }
      }
    }
  })
};

fetch('https://mavi-backend.memories.ai/serve/api/v2/iu/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_URL => "https://mavi-backend.memories.ai/serve/api/v2/iu/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([
    'model' => 'qwen:qwen3-vl-plus',
    'messages' => [
        [
                'content' => '<string>'
        ]
    ],
    'temperature' => 0.7,
    'max_tokens' => 1024,
    'top_p' => 0.9,
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'n' => 1,
    'stream' => false,
    'stop' => '<string>',
    'extra_body' => [
        'metadata' => [
                'enable_thinking' => true,
                'thinking_budget' => 123,
                'response_format' => [
                                'type' => 'json_schema',
                                'json_schema' => [
                                                                'name' => '<string>',
                                                                'schema' => [
                                                                                                                                'type' => 'object',
                                                                                                                                'properties' => [
                                                                                                                                                                                                                                                                
                                                                                                                                ],
                                                                                                                                'required' => [
                                                                                                                                                                                                                                                                '<string>'
                                                                                                                                ]
                                                                ]
                                ]
                ]
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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 := "https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"qwen:qwen3-vl-plus\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 0.7,\n  \"max_tokens\": 1024,\n  \"top_p\": 0.9,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"n\": 1,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"extra_body\": {\n    \"metadata\": {\n      \"enable_thinking\": true,\n      \"thinking_budget\": 123,\n      \"response_format\": {\n        \"type\": \"json_schema\",\n        \"json_schema\": {\n          \"name\": \"<string>\",\n          \"schema\": {\n            \"type\": \"object\",\n            \"properties\": {},\n            \"required\": [\n              \"<string>\"\n            ]\n          }\n        }\n      }\n    }\n  }\n}")

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

	req.Header.Add("Authorization", "<api-key>")
	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("https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"qwen:qwen3-vl-plus\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 0.7,\n  \"max_tokens\": 1024,\n  \"top_p\": 0.9,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"n\": 1,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"extra_body\": {\n    \"metadata\": {\n      \"enable_thinking\": true,\n      \"thinking_budget\": 123,\n      \"response_format\": {\n        \"type\": \"json_schema\",\n        \"json_schema\": {\n          \"name\": \"<string>\",\n          \"schema\": {\n            \"type\": \"object\",\n            \"properties\": {},\n            \"required\": [\n              \"<string>\"\n            ]\n          }\n        }\n      }\n    }\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"qwen:qwen3-vl-plus\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 0.7,\n  \"max_tokens\": 1024,\n  \"top_p\": 0.9,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"n\": 1,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"extra_body\": {\n    \"metadata\": {\n      \"enable_thinking\": true,\n      \"thinking_budget\": 123,\n      \"response_format\": {\n        \"type\": \"json_schema\",\n        \"json_schema\": {\n          \"name\": \"<string>\",\n          \"schema\": {\n            \"type\": \"object\",\n            \"properties\": {},\n            \"required\": [\n              \"<string>\"\n            ]\n          }\n        }\n      }\n    }\n  }\n}"

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

{
  "id": "6612267a-d08f-9ea0-a254-7bcea6339f49",
  "object": "completion",
  "model": "qwen3-vl-plus",
  "created_at": 1767094289,
  "status": "completed",
  "choices": [
    {
      "text": "This image is from the game Half-Life 2, showing a game scene from a first-person perspective.\n\nIn the scene, the player holds a \"Gravity Gun\" in each hand, aiming at the wall ahead. A yellow \"Mandatory Reminder\" sign hangs on the wall, printed with the U.S. national emblem pattern and inscribed with \"AMENDMENT 35\" (35th Amendment), with text below reading: \"No person shall be found with fewer than thirteen times their own body weight of federally provisioned munitions.\" - This is clearly a fictional absurd law within the game.\n\nThe bottom left corner of the screen shows the player's \"HEALTH\" and \"SUIT\" both at 100. The bottom right corner displays ammunition information \"IDC ANYMORE AMMO\", suggesting ample or infinite ammunition.\n\nThe entire scene is full of dark humor and dystopian style, one of the iconic scenes from Half-Life 2, often used by players as memes or screenshots for sharing.",
      "index": 0
    }
  ],
  "usage": {
    "input_tokens": 235,
    "output_tokens": 229,
    "total_tokens": 464
  },
  "meta": {
    "provider": "qwen",
    "provider_model": "qwen3-vl-plus"
  }
}

Product: Visual Intelligence — Image Model APIs (atomic) Use case: Call an Image Language Model (Gemini / GPT / Nova / Qwen) directly with your own prompt. Full control over model and parameters. Host: https://mavi-backend.memories.ai/serve/api/v2 Auth: Authorization: sk-mavi-... (no Bearer prefix)

This endpoint allows you to generate chat completions with image inputs using Qwen ILM model.

Endpoint: POST https://mavi-backend.memories.ai/serve/api/v2/iu/chat/completionsImage Understanding (ILM) endpoints use the /iu path prefix. Video Understanding (VLM) endpoints use /vu instead.

Supported Models

All models require the qwen: prefix when used in the model parameter (e.g., qwen:qwen3-vl-plus).

Qwen 3 VL Plus (Premium - Tiered Pricing)

Model	Input Price	Output Price
qwen3-vl-plus	$0.00021/1K (≤32K), $0.00031/1K (32K-128K), $0.00063/1K (128K-256K)	$0.00168/1K (≤32K), $0.00252/1K (32K-128K), $0.00503/1K (128K-256K)
qwen3-vl-plus-2025-12-19	$0.00021/1K (≤32K), $0.00031/1K (32K-128K), $0.00063/1K (128K-256K)	$0.00168/1K (≤32K), $0.00252/1K (32K-128K), $0.00503/1K (128K-256K)
qwen3-vl-plus-2025-09-23	$0.00021/1K (≤32K), $0.00031/1K (32K-128K), $0.00063/1K (128K-256K)	$0.00168/1K (≤32K), $0.00252/1K (32K-128K), $0.00503/1K (128K-256K)

Qwen 3 VL Flash (Cost-Effective - Tiered Pricing)

Model	Input Price	Output Price
qwen3-vl-flash	$0.000052/1K (≤32K), $0.000079/1K (32K-128K), $0.000126/1K (128K-256K)	$0.00042/1K (≤32K), $0.00063/1K (32K-128K), $0.00101/1K (128K-256K)
qwen3-vl-flash-2025-10-15	$0.000052/1K (≤32K), $0.000079/1K (32K-128K), $0.000126/1K (128K-256K)	$0.00042/1K (≤32K), $0.00063/1K (32K-128K), $0.00101/1K (128K-256K)

Qwen VL Max (Legacy)

Model	Input Price	Output Price
qwen-vl-max	$0.00084/1K tokens	$0.00335/1K tokens
qwen-vl-max-latest	$0.00084/1K tokens	$0.00335/1K tokens
qwen-vl-max-2025-08-13	$0.00084/1K tokens	$0.00335/1K tokens
qwen-vl-max-2025-04-08	$0.00084/1K tokens	$0.00335/1K tokens

Qwen VL Plus (Legacy)

Model	Input Price	Output Price
qwen-vl-plus	$0.00022/1K tokens	$0.00066/1K tokens
qwen-vl-plus-latest	$0.00022/1K tokens	$0.00066/1K tokens
qwen-vl-plus-2025-08-15	$0.00022/1K tokens	$0.00066/1K tokens
qwen-vl-plus-2025-05-07	$0.00022/1K tokens	$0.00066/1K tokens
qwen-vl-plus-2025-01-25	$0.00022/1K tokens	$0.00066/1K tokens

Pricing Notes:

All prices are per 1,000 tokens and converted from CNY at exchange rate of 7.0
Tip: To compare with other providers (who price per 1M tokens), multiply these prices by 1,000. For example, $0.00021/1K = $0.21/1M tokens
Qwen 3 VL models support tiered pricing: ≤32K, 32K-128K, 128K-256K token ranges
Legacy models (Qwen VL Max/Plus) use flat-rate pricing
Remember to include the qwen: prefix: "model": "qwen:qwen3-vl-plus"

Request Body

Parameter	Type	Required	Default	Description
model	string	Yes	-	The model to use (e.g., `qwen:qwen3-vl-plus`)
messages	array	Yes	-	Array of message objects. Each message contains: - `role`: Role type, values: `system`, `user` - `content`: Message content, can be a string or array. Array items can contain: - `image`: Image URL or base64 encoded image - `text`: Text content
temperature	number	No	0.7	Controls randomness: 0.0-2.0, higher = more random
max_tokens	integer	No	1024	Maximum number of tokens to generate
top_p	number	No	0.9	Nucleus sampling: 0.0-1.0, consider tokens with top_p probability mass
frequency_penalty	number	No	0.0	Reduces repetition of frequent tokens: -2.0 to 2.0
presence_penalty	number	No	0.0	Increases likelihood of new topics: -2.0 to 2.0
n	integer	No	1	Number of completions to generate
stream	boolean	No	false	Whether to stream the response
stop	string \| array \| null	No	null	Stop sequences. Can be a string, array of strings, or null
extra_body	object	No	-	Additional body parameters. Contains: - `metadata`: Metadata object - `enable_thinking`: Boolean to enable thinking mode - `thinking_budget`: Integer value for thinking budget - `response_format`: Response format configuration - `type`: Format type (`json_schema`) - `json_schema`: JSON schema object - `name`: Schema name - `schema`: JSON schema definition

Code Example

from openai import OpenAI

client = OpenAI(
    api_key="sk-mavi-...",
    base_url="https://mavi-backend.memories.ai/serve/api/v2/iu"
)

resp = client.chat.completions.create(
    model="qwen:qwen3-vl-plus",
    messages=[
        {"role": "system", "content": "You are a multimodal assistant. Keep your answers concise."},
        {
            "role": "user",
            "content": [
                {
                    "image": "https://storage.googleapis.com/memories-test-data/gun5.png"  # url or base64
                },
                {"text": "What is the content of this image?"}
            ]
        }
    ],
    temperature=0.7,  # Controls randomness: 0.0-2.0, higher = more random
    max_tokens=1024,  # Maximum number of tokens to generate
    top_p=0.9,  # Nucleus sampling: 0.0-1.0, consider tokens with top_p probability mass
    frequency_penalty=0.0,  # -2.0 to 2.0, reduces repetition of frequent tokens
    presence_penalty=0.0,  # -2.0 to 2.0, increases likelihood of new topics
    n=1,  # Number of completions to generate
    stream=False,  # Whether to stream the response
    stop=None,  # Stop sequences (list of strings)
    extra_body={
        "metadata": {
            "enable_thinking": True,
            "thinking_budget": 1024,
            "response_format": {
                "type": "json_schema",
                "json_schema": {
                    "name": "answer",
                    "schema": {
                        "type": "object",
                        "properties": {
                            "result": {"type": "string"}
                        },
                        "required": ["result"]
                    }
                }
            }
        }
    }
)
print(resp)

Response

Returns the chat completion response with structured output.

{
  "id": "6612267a-d08f-9ea0-a254-7bcea6339f49",
  "object": "completion",
  "model": "qwen3-vl-plus",
  "created_at": 1767094289,
  "status": "completed",
  "choices": [
    {
      "text": "This image is from the game Half-Life 2, showing a game scene from a first-person perspective.\n\nIn the scene, the player holds a \"Gravity Gun\" in each hand, aiming at the wall ahead. A yellow \"Mandatory Reminder\" sign hangs on the wall, printed with the U.S. national emblem pattern and inscribed with \"AMENDMENT 35\" (35th Amendment), with text below reading: \"No person shall be found with fewer than thirteen times their own body weight of federally provisioned munitions.\" - This is clearly a fictional absurd law within the game.\n\nThe bottom left corner of the screen shows the player's \"HEALTH\" and \"SUIT\" both at 100. The bottom right corner displays ammunition information \"IDC ANYMORE AMMO\", suggesting ample or infinite ammunition.\n\nThe entire scene is full of dark humor and dystopian style, one of the iconic scenes from Half-Life 2, often used by players as memes or screenshots for sharing.",
      "index": 0
    }
  ],
  "usage": {
    "input_tokens": 235,
    "output_tokens": 229,
    "total_tokens": 464
  },
  "meta": {
    "provider": "qwen",
    "provider_model": "qwen3-vl-plus"
  }
}

Response Parameters

Parameter	Type	Description
id	string	Unique identifier for the completion
object	string	Object type, always “completion”
model	string	The model used for the completion
created_at	integer	Unix timestamp of when the completion was created
status	string	Status of the completion (e.g., “completed”)
choices	array	Array of completion choices
choices[].text	string	Text content of the completion
choices[].index	integer	Index of the choice in the choices array
usage	object	Token usage information
usage.input_tokens	integer	Number of input tokens used
usage.output_tokens	integer	Number of output tokens generated
usage.total_tokens	integer	Total number of tokens used
meta	object	Metadata about the completion
meta.provider	string	Provider name (e.g., “qwen”)
meta.provider_model	string	Provider-specific model name

Authorizations

Authorization

string

header

required

Body

application/json

model

string

required

The model to use (e.g., qwen:qwen3-vl-plus)

Example:

"qwen:qwen3-vl-plus"

messages

object[]

required

Array of message objects

Show child attributes

temperature

number

default:0.7

Controls randomness: 0.0-2.0, higher = more random

Required range: 0 <= x <= 2

max_tokens

integer

default:1024

Maximum number of tokens to generate

top_p

number

default:0.9

Nucleus sampling: 0.0-1.0

Required range: 0 <= x <= 1

frequency_penalty

number

default:0

Reduces repetition of frequent tokens: -2.0 to 2.0

Required range: -2 <= x <= 2

presence_penalty

number

default:0

Increases likelihood of new topics: -2.0 to 2.0

Required range: -2 <= x <= 2

integer

default:1

Number of completions to generate

stream

boolean

default:false

Whether to stream the response

stop

Stop sequences

extra_body

object

Show child attributes

Response

200 - application/json

Chat completion response with structured output

string

required

Unique identifier for the completion

Example:

"6612267a-d08f-9ea0-a254-7bcea6339f49"

object

string

required

Object type, always 'completion'

Example:

"completion"

model

string

required

The model used for the completion

Example:

"qwen3-vl-plus"

created_at

integer

required

Unix timestamp of when the completion was created

Example:

1767094289

status

string

required

Status of the completion

Example:

"completed"

choices

object[]

required

Show child attributes

usage

object

required

Show child attributes

Get Started

Asset Management

Social Media Scraping

Audio File Transcription

Live Audio Transcription

Video Model APIs

Video Task APIs

Live Video Content Moderation

Live Video Understanding

Image Model APIs

Embeddings

Human ReID & Caption

Reference

Supported Models

Qwen 3 VL Plus (Premium - Tiered Pricing)

Qwen 3 VL Flash (Cost-Effective - Tiered Pricing)

Qwen VL Max (Legacy)

Qwen VL Plus (Legacy)

Request Body

Code Example

Response

Response Parameters

Authorizations

Body

Response

​Supported Models

​Qwen 3 VL Plus (Premium - Tiered Pricing)

​Qwen 3 VL Flash (Cost-Effective - Tiered Pricing)

​Qwen VL Max (Legacy)

​Qwen VL Plus (Legacy)

​Request Body

​Code Example

​Response

​Response Parameters

Authorizations

Body

Response

Supported Models

Qwen 3 VL Plus (Premium - Tiered Pricing)

Qwen 3 VL Flash (Cost-Effective - Tiered Pricing)

Qwen VL Max (Legacy)

Qwen VL Plus (Legacy)

Request Body

Code Example

Response

Response Parameters