Qwen 3.5 Flash API nasıl kullanılır?

Qwen 3.5 Flash modelini Parel API ile kullanmak için OpenAI SDK'sını yükleyin, base_url olarak https://api.parel.cloud/v1 belirleyin ve model parametresine "qwen3.5-flash" yazın. Python, Node.js, Java, C# ve cURL desteklenir.

Qwen 3.5 Flash KVKK uyumlu mu?

Qwen 3.5 Flash DashScope AP Southeast sunucularında çalışır. KVKK uyumlu alternatifler için Parel edge modellerine bakabilirsiniz.

Alibaba

Qwen 3.5 Flash

Düşük gecikme ve yüksek hız, genel amaçlı LLM

Input 50 kredi/1M token

Output 100 kredi/1M token

Playground'da Dene

LLM 1M token Vision Tool Use

Hakkında

Qwen 3.5 Flash, Alibaba tarafından geliştirilen hızlı ve maliyet etkin bir yapay zeka modelidir. 1M token bağlam penceresi ile büyük doküman analizi, RAG (Retrieval-Augmented Generation) ve toplu veri işleme görevlerinde verimli performans sunar. MoE mimarisi düşük maliyet ve yüksek hız sağlar. Parel API ile büyük ölçekli metin işleme ve arama projelerinize entegre edilebilir.

Kullanım Alanları

› Chatbot ve müşteri destek otomasyonu
› İçerik üretimi ve metin özeti
› Görsel analiz ve belge okuma (OCR)
› RAG (Retrieval-Augmented Generation) sistemleri

Aile

Qwen 3.5

Mimari

Transformer (MoE)

Parametreler

Bilinmiyor

Lisans

Proprietary

Veri Merkezi

DashScope AP Southeast

Provider: Alibaba
Tür: LLM
Context: 1M token
Model ID: qwen3.5-flash
Input Fiyat: 50 kredi/1M token
Output Fiyat: 100 kredi/1M token

Benzer Modeller

Qwen Turbo

Alibaba · 131K

Qwen 3.5 Plus

Alibaba · 131K

Daha pahalı, daha güçlü

Qwen 3 Coder Plus

Alibaba · 131K

Daha pahalı, daha güçlü

OpenAI SDK ile dakikalar içinde entegre edin.

Ücretsiz Başla Tüm Modeller

Authentication #

API anahtarınızı ortam değişkeni olarak tanımlayın.

python

import os
os.environ["OPENAI_API_KEY"] = "pk-..."

Kurulum #

OpenAI SDK'yi yükleyin.

python

pip install openai

Chat Completions #

Temel sohbet tamamlama isteği.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.parel.cloud/v1",
    api_key="pk-...",
)

response = client.chat.completions.create(
    model="qwen3.5-flash",
    messages=[
        {"role": "user", "content": "Merhaba!"}
    ],
)

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

javascript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.parel.cloud/v1",
  apiKey: "pk-...",
});

const response = await client.chat.completions.create({
  model: "qwen3.5-flash",
  messages: [
    { role: "user", content: "Merhaba!" }
  ],
});

console.log(response.choices[0].message.content);

java

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.*;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://api.parel.cloud/v1")
    .apiKey("pk-...")
    .build();

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("qwen3.5-flash")
    .addUserMessage("Merhaba!")
    .build();

ChatCompletion completion = client.chat().completions().create(params);

System.out.println(completion.choices().get(0).message().content().get());

csharp

using OpenAI;
using OpenAI.Chat;

ChatClient client = new(
    model: "qwen3.5-flash",
    credential: new ApiKeyCredential("pk-..."),
    options: new OpenAIClientOptions {
        Endpoint = new Uri("https://api.parel.cloud/v1") }
);

ChatCompletion completion = client.CompleteChat(
    new UserChatMessage("Merhaba!")
);

Console.WriteLine(completion.Content[0].Text);

bash

curl -X POST https://api.parel.cloud/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer pk-..." \
  -d '{
    "model": "qwen3.5-flash",
    "messages": [
      {"role": "user", "content": "Merhaba!"}
    ]
  }'

Streaming #

Yanıtları token token akın halinde alın.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.parel.cloud/v1",
    api_key="pk-...",
)

stream = client.chat.completions.create(
    model="qwen3.5-flash",
    messages=[
        {"role": "user", "content": "Türkiye'nin başkenti neresidir?"}
    ],
    stream=True,
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

javascript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.parel.cloud/v1",
  apiKey: "pk-...",
});

const stream = await client.chat.completions.create({
  model: "qwen3.5-flash",
  messages: [
    { role: "user", content: "Türkiye'nin başkenti neresidir?" }
  ],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

java

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.*;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://api.parel.cloud/v1")
    .apiKey("pk-...")
    .build();

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("qwen3.5-flash")
    .addUserMessage("Türkiye'nin başkenti neresidir?")
    .stream(true)
    .build();

client.chat().completions().createStreaming(params)
    .stream()
    .flatMap(completion -> completion.choices().stream())
    .forEach(choice -> {
        choice.delta().content().ifPresent(System.out::print);
    });

csharp

using OpenAI;
using OpenAI.Chat;

ChatClient client = new(
    model: "qwen3.5-flash",
    credential: new ApiKeyCredential("pk-..."),
    options: new OpenAIClientOptions {
        Endpoint = new Uri("https://api.parel.cloud/v1") }
);

AsyncCollectionResult<StreamingChatCompletionUpdate> updates =
    client.CompleteChatStreamingAsync(
        new UserChatMessage("Türkiye'nin başkenti neresidir?")
    );

await foreach (StreamingChatCompletionUpdate update in updates)
{
    foreach (ChatMessageContentPart part in update.ContentUpdate)
    {
        Console.Write(part.Text);
    }
}

bash

curl -X POST https://api.parel.cloud/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer pk-..." \
  -d '{
    "model": "qwen3.5-flash",
    "messages": [
      {"role": "user", "content": "Türkiye\'nin başkenti neresidir?"}
    ],
    "stream": true
  }'

System Prompt #

Modelin davranisini system mesajiyla yonlendirin.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.parel.cloud/v1",
    api_key="pk-...",
)

response = client.chat.completions.create(
    model="qwen3.5-flash",
    messages=[
        {
            "role": "system",
            "content": "Sen yardimci bir Turkce asistansin. Kisa ve net cevaplar ver."
        },
        {
            "role": "user",
            "content": "KVKK nedir?"
        }
    ],
)

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

javascript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.parel.cloud/v1",
  apiKey: "pk-...",
});

const response = await client.chat.completions.create({
  model: "qwen3.5-flash",
  messages: [
    {
      role: "system",
      content: "Sen yardimci bir Turkce asistansin. Kisa ve net cevaplar ver."
    },
    {
      role: "user",
      content: "KVKK nedir?"
    }
  ],
});

console.log(response.choices[0].message.content);

java

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.*;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://api.parel.cloud/v1")
    .apiKey("pk-...")
    .build();

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("qwen3.5-flash")
    .addSystemMessage("Sen yardimci bir Turkce asistansin. Kisa ve net cevaplar ver.")
    .addUserMessage("KVKK nedir?")
    .build();

ChatCompletion completion = client.chat().completions().create(params);

System.out.println(completion.choices().get(0).message().content().get());

csharp

using OpenAI;
using OpenAI.Chat;

ChatClient client = new(
    model: "qwen3.5-flash",
    credential: new ApiKeyCredential("pk-..."),
    options: new OpenAIClientOptions {
        Endpoint = new Uri("https://api.parel.cloud/v1") }
);

ChatCompletion completion = client.CompleteChat(
    new SystemChatMessage("Sen yardimci bir Turkce asistansin. Kisa ve net cevaplar ver."),
    new UserChatMessage("KVKK nedir?")
);

Console.WriteLine(completion.Content[0].Text);

bash

curl -X POST https://api.parel.cloud/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer pk-..." \
  -d '{
    "model": "qwen3.5-flash",
    "messages": [
      {"role": "system", "content": "Sen yardimci bir Turkce asistansin."},
      {"role": "user", "content": "KVKK nedir?"}
    ]
  }'

Parametreler #

Yanıt kalitesini ve çeşitliliğini ayarlayın.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.parel.cloud/v1",
    api_key="pk-...",
)

response = client.chat.completions.create(
    model="qwen3.5-flash",
    messages=[
        {"role": "user", "content": "Yaratici bir hikaye yaz."}
    ],
    temperature=0.9,    # 0-2: dusuk = deterministik, yuksek = yaratici
    max_tokens=2048,    # maksimum cikti token sayisi
    top_p=0.95,         # nucleus sampling esigi
)

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

javascript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.parel.cloud/v1",
  apiKey: "pk-...",
});

const response = await client.chat.completions.create({
  model: "qwen3.5-flash",
  messages: [
    { role: "user", content: "Yaratici bir hikaye yaz." }
  ],
  temperature: 0.9,    // 0-2: dusuk = deterministik, yuksek = yaratici
  max_tokens: 2048,    // maksimum cikti token sayisi
  top_p: 0.95,         // nucleus sampling esigi
});

console.log(response.choices[0].message.content);

java

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.*;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://api.parel.cloud/v1")
    .apiKey("pk-...")
    .build();

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model("qwen3.5-flash")
    .addUserMessage("Yaratici bir hikaye yaz.")
    .temperature(0.9)    // 0-2: dusuk = deterministik, yuksek = yaratici
    .maxTokens(2048)     // maksimum cikti token sayisi
    .topP(0.95)          // nucleus sampling esigi
    .build();

ChatCompletion completion = client.chat().completions().create(params);

System.out.println(completion.choices().get(0).message().content().get());

csharp

using OpenAI;
using OpenAI.Chat;

ChatClient client = new(
    model: "qwen3.5-flash",
    credential: new ApiKeyCredential("pk-..."),
    options: new OpenAIClientOptions {
        Endpoint = new Uri("https://api.parel.cloud/v1") }
);

ChatCompletionOptions options = new()
{
    Temperature = 0.9f,   // 0-2: dusuk = deterministik, yuksek = yaratici
    MaxOutputTokenCount = 2048,  // maksimum cikti token sayisi
    TopP = 0.95f,         // nucleus sampling esigi
};

ChatCompletion completion = client.CompleteChat(
    new List<ChatMessage> {
        new UserChatMessage("Yaratici bir hikaye yaz.")
    },
    options
);

Console.WriteLine(completion.Content[0].Text);

bash

curl -X POST https://api.parel.cloud/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer pk-..." \
  -d '{
    "model": "qwen3.5-flash",
    "messages": [
      {"role": "user", "content": "Yaratici bir hikaye yaz."}
    ],
    "temperature": 0.9,
    "max_tokens": 2048,
    "top_p": 0.95
  }'

Kayıt olun, API anahtarınızı alın.

Hemen Başla Tum Modeller