NeuralBridgeDocumentation

Qwen3 VL Plus

unofficialchat
DeveloperAlibaba
Identifierqwen/qwen3-vl-plus-01402

Qwen3 VL Plus specifications

Context window262K
Max output tokens32768
Release date
InputText, Image
OutputText

Qwen3 VL Plus pricing in rubles

You pay for what you use, per token and per unit. The final request cost is returned in the API response.

TypePrice
Input tokens36per 1M tokens
Output tokens288per 1M tokens
Cache read7,2per 1M tokens

Prices are in rubles and may change with exchange rates.

What Qwen3 VL Plus can do

Qwen3 VL Plus API: connection and code examples

The service exposes a single OpenAI-compatible API. Set our base_url and the key from your dashboard.

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.neuralbridge.ru/v1",
)

response = client.chat.completions.create(
    model="qwen/qwen3-vl-plus-01402",
    messages=[{"role": "user", "content": "Привет! Расскажи о себе."}],
)

print(response.choices[0].message.content)

Python (requests)

import requests

response = requests.post(
    "https://api.neuralbridge.ru/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "qwen/qwen3-vl-plus-01402",
        "messages": [{"role": "user", "content": "Привет! Расскажи о себе."}],
    },
)

print(response.json()["choices"][0]["message"]["content"])

cURL

curl https://api.neuralbridge.ru/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-vl-plus-01402",
    "messages": [{"role": "user", "content": "Привет! Расскажи о себе."}]
  }'

API endpoints

POST /v1/chat/completionsprimaryChat Completions
Chat asosiy endpointi: xabarlar tarixini qabul qiladi va model javobini qaytaradi. Oqimli va oddiy rejimlarni qo‘llab-quvvatlaydi.
POST /v1/responsesResponses
Holat va tuzilgan chiqish bilan chatning muqobil formati.
POST /v1/messagesMessages
Anthropic formati: Claude uchun yozilgan mijozlar va SDKlar uchun bir xil chat.
POST /v1/converseConverse
Amazon Bedrock Converse formati — uni uchun yozilgan mijozlar uchun.
POST /v1/converse-streamConverse Stream
Bedrock Converse formatining oqimli varianti.
POST /v1/generateContentGenerate Content
Google Gemini formati — mijozlar va unga mo‘ljallangan SDKlar uchun.
POST /v1/streamGenerateContentStream Generate Content
Gemini formatining oqimli varianti.

Supported request parameters

ParameterDefaultAllowed valuesDescription
temperature1Javobning xilma-xilligiga ta'sir qiladi: qiymat qanchalik yuqori bo'lsa, chiqish shunchalik tasodifiy, past bo'lsa, shunchalik oldindan aytib bo'ladigan.
top_p1Eng ehtimoliy tokenlarning ulush tanlovini cheklaydi: faqat ehtimolliklari yig'indisi P ga teng bo'lgan tokenlar hisobga olinadi.
max_tokensModel javobda yaratishi mumkin bo‘lgan tokenlar sonining yuqori chegarasi.
presence_penalty0Agar token matnda allaqachon uchragan bo‘lsa, uning ehtimoli kamayadi — model yangi mavzularga osonroq o‘tadi.
frequency_penalty0Token ehtimolini u qanchalik tez-tez uchraganiga proporsional ravishda kamaytiradi — takrorlanishlarga qarshi kurashadi.
stopCheklovchi satrlar ro‘yxati: model har qanday birini chiqarishi bilan generatsiya to‘xtatiladi.
seedTasodifiylikni qat'iy belgilaydi: bir xil seed va bir xil parametrlar bilan takroriy so‘rov bir xil natija beradi.
response_formatJavob formati: oddiy matn yoki berilgan sxema bo‘yicha qat'iy JSON.
streamfalseJavobni generatsiya jarayonida oqim sifatida berish, oxirida bitta bo‘lak sifatida emas.
tools
tool_choice
parallel_tool_calls
Language:РусскийEnglishУкраїнськаБеларускаяҚазақшаOʻzbekchaКыргызчаТоҷикӣՀայերենAzərbaycancaTürkmençeRomânăDeutschFrançaisEspañolItalianoPortuguêsPolskiNederlandsTürkçeΕλληνικά