DeepSeek-SiliconFlow

Python

Sample code

from openai import OpenAI
import os

# Initialize the OpenAI client
client = OpenAI(
    # If the environment variable is not configured, replace with your Alibaba Cloud Model Studio API Key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)

messages = [{"role": "user", "content": "Who are you?"}]
completion = client.chat.completions.create(
    model="siliconflow/deepseek-v3.2",
    messages=messages,
    # Enable thinking mode by setting enable_thinking in extra_body
    extra_body={"enable_thinking": True},
    stream=True,
    stream_options={
        "include_usage": True
    },
)

reasoning_content = ""  # Full thinking process
answer_content = ""  # Full response
is_answering = False  # Tracks if the model has started answering
print("\n" + "=" * 20 + "Thinking Process" + "=" * 20 + "\n")

for chunk in completion:
    if not chunk.choices:
        print("\n" + "=" * 20 + "token usage" + "=" * 20 + "\n")
        print(chunk.usage)
        continue

    delta = chunk.choices[0].delta

    # Collect only the thinking content
    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
        reasoning_content += delta.reasoning_content

    # When content is received, start the response
    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Full Response" + "=" * 20 + "\n")
            is_answering = True
        print(delta.content, end="", flush=True)
        answer_content += delta.content

Response

====================Thinking Process====================

Ah, the user is asking who I am, which is a simple self-introduction question. I need to clearly state my identity, development background, core functions, and features, without overcomplicating things.

I can start with my company background and AI identity, then list key capabilities to help the user quickly understand my value. Finally, I'll use a friendly tone to remain open. I thought about highlighting practical points like being free, having a long context, and processing files, and adding an emoji to seem more approachable.

I should avoid technical details and focus on what the user can directly perceive.
====================Full Response====================

Hello! I am DeepSeek, an AI assistant created by DeepSeek!

I am a text-only model with a 128K context length, and I am completely free for everyone to use. While I don't support multimodal recognition, I can help you process uploaded images, txt, pdf, ppt, word, and excel files by extracting and analyzing their text content.

My knowledge cutoff is July 2024, and I also support web search (you need to manually enable it). You can download my app from the official app store.

I am happy to help you with various questions, whether they are about studying, work, life, or creative projects. I will provide enthusiastic and detailed assistance! Is there anything you would like to know or need my help with?
====================token usage====================

CompletionUsage(completion_tokens=239, prompt_tokens=5, total_tokens=244, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=None, audio_tokens=None, reasoning_tokens=95, rejected_prediction_tokens=None, text_tokens=144), prompt_tokens_details=None)

Node.js

Sample code

import OpenAI from "openai";
import process from 'process';

// Initialize the OpenAI client
const openai = new OpenAI({
    // If the environment variable is not configured, replace with your Alibaba Cloud Model Studio API Key: apiKey: "sk-xxx"
    apiKey: process.env.DASHSCOPE_API_KEY,
    // China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
    baseURL: 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1'
});

let reasoningContent = ''; // Full thinking process
let answerContent = ''; // Full response
let isAnswering = false; // Tracks if the model has started answering

async function main() {
    try {
        const messages = [{ role: 'user', content: 'Who are you?' }];

        const stream = await openai.chat.completions.create({
            model: 'siliconflow/deepseek-v3.2',
            messages,
            // Note: In the Node.js SDK, non-standard parameters like enable_thinking are passed as top-level properties, not within extra_body.
            enable_thinking: true,
            stream: true,
            stream_options: {
                include_usage: true
            },
        });

        console.log('\n' + '='.repeat(20) + 'Thinking Process' + '='.repeat(20) + '\n');

        for await (const chunk of stream) {
            if (!chunk.choices?.length) {
                console.log('\n' + '='.repeat(20) + 'token usage' + '='.repeat(20) + '\n');
                console.log(chunk.usage);
                continue;
            }

            const delta = chunk.choices[0].delta;

            // Collect only the thinking content
            if (delta.reasoning_content !== undefined && delta.reasoning_content !== null) {
                if (!isAnswering) {
                    process.stdout.write(delta.reasoning_content);
                }
                reasoningContent += delta.reasoning_content;
            }

            // When content is received, start the response
            if (delta.content !== undefined && delta.content) {
                if (!isAnswering) {
                    console.log('\n' + '='.repeat(20) + 'Full Response' + '='.repeat(20) + '\n');
                    isAnswering = true;
                }
                process.stdout.write(delta.content);
                answerContent += delta.content;
            }
        }
    } catch (error) {
        console.error('Error:', error);
    }
}

main();

Response

====================Thinking Process====================

Ah, the user is asking a very basic self-introduction question. This type of question doesn't require complex deconstruction; I can just provide a standard identity description.

I need to state that I am an AI assistant from DeepSeek and list my core features so the user can quickly understand my capabilities. I'll end with an enthusiastic but concise tone and guide the user to make a specific request.

I should keep the response structure clear but not too rigid, and add some emojis to seem friendly.
====================Full Response====================

Hello! I am DeepSeek, an AI assistant created by DeepSeek!

I am a text-only model and I am good at answering various questions, assisting with writing, analyzing problems, programming, and more. While I don't support multimodal recognition, I can process uploaded images, txt, pdf, ppt, word, and excel files by extracting and analyzing their text content.

I am completely free to use, have a 128K context length, and support web search (you need to manually enable it). You can also download my app version from the official app store.

My knowledge cutoff is July 2024, and I will provide help in an enthusiastic and detailed manner. If you have any questions or need assistance, just let me know! I'll do my best to help you!
====================token usage====================

{
  prompt_tokens: 5,
  completion_tokens: 226,
  total_tokens: 231,
  completion_tokens_details: { reasoning_tokens: 81, text_tokens: 145 }
}

HTTP

Sample code

# China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
curl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "siliconflow/deepseek-v3.2",
    "messages": [
        {
            "role": "user",
            "content": "Who are you?"
        }
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    },
    "enable_thinking": true
}'

Python

Sample code

import os
import dashscope
from dashscope import Generation

# The following is the configuration for the China (Beijing) region. Replace {WorkspaceId} with your actual workspace ID when making a call. Configurations vary by region.
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"

# Initialize request parameters
messages = [{"role": "user", "content": "Who are you?"}]

completion = Generation.call(
    # If the environment variable is not configured, replace with your Alibaba Cloud Model Studio API Key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="siliconflow/deepseek-v3.2",
    messages=messages,
    result_format="message",  # Set the result format to message
    enable_thinking=True,
    stream=True,              # Enable streaming output
    incremental_output=True,  # Enable incremental output
)

reasoning_content = ""  # Full thinking process
answer_content = ""     # Full response
is_answering = False    # Tracks if the model has started answering

print("\n" + "=" * 20 + "Thinking Process" + "=" * 20 + "\n")

for chunk in completion:
    message = chunk.output.choices[0].message
    # Collect only the thinking content
    if "reasoning_content" in message:
        if not is_answering:
            print(message.reasoning_content, end="", flush=True)
        reasoning_content += message.reasoning_content

    # When content is received, start the response
    if message.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Full Response" + "=" * 20 + "\n")
            is_answering = True
        print(message.content, end="", flush=True)
        answer_content += message.content

print("\n" + "=" * 20 + "token usage" + "=" * 20 + "\n")
print(chunk.usage)

Response

====================Thinking Process====================

Hmm, the user asked a very basic self-introduction question. This kind of question doesn't require complex deconstruction; I just need to state my identity and core functions.

I can respond with a clear and concise structure: first, state my AI identity, then introduce my capabilities in sections, and finally end with an open-ended question to continue the conversation. Avoid being too verbose and maintain information density.

I need to be particularly careful to maintain a friendly but professional tone, use emojis to adjust the mood but not excessively. Mentioning the knowledge cutoff date and the fact that I am free can increase credibility, and ending with "at your service" can reinforce a sense of helpfulness.
====================Full Response====================

Hello! I am DeepSeek, an AI assistant created by DeepSeek!

I am a text-only model and I am good at answering various questions, assisting with writing, analyzing problems, programming, and more. While I don't support multimodal recognition, I can process uploaded images, txt, pdf, ppt, word, and excel files by reading their text content.

Some of my features:
- Completely free to use, no payment plans
- Supports a 128K context length
- App available for download from the official app store
- Supports web search (needs to be enabled manually)
- Knowledge cutoff: July 2024

I am happy to be your learning and work partner. Whether it's for daily chats, answering questions, or assisting with complex tasks, I will provide enthusiastic and detailed help! What can I do for you?
====================token usage====================

{"input_tokens": 6, "output_tokens": 265, "total_tokens": 271, "output_tokens_details": {"reasoning_tokens": 103, "text_tokens": 162}}

Java

Sample code

// DashScope SDK version >= 2.19.4
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import io.reactivex.Flowable;
import java.lang.System;
import java.util.Arrays;
import com.alibaba.dashscope.utils.Constants;

public class Main {
    static {
        // The following is the configuration for the China (Beijing) region. Replace {WorkspaceId} with your actual workspace ID when making a call. Configurations vary by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";
    }

    private static StringBuilder reasoningContent = new StringBuilder();
    private static StringBuilder finalContent = new StringBuilder();
    private static boolean isFirstPrint = true;
    private static void handleGenerationResult(GenerationResult message) {
        String reasoning = message.getOutput().getChoices().get(0).getMessage().getReasoningContent();
        String content = message.getOutput().getChoices().get(0).getMessage().getContent();
        if (reasoning != null && !reasoning.isEmpty()) {
            reasoningContent.append(reasoning);
            if (isFirstPrint) {
                System.out.println("====================Thinking Process====================");
                isFirstPrint = false;
            }
            System.out.print(reasoning);
        }
        if (content != null && !content.isEmpty()) {
            finalContent.append(content);
            if (!isFirstPrint) {
                System.out.println("\n====================Full Response====================");
                isFirstPrint = true;
            }
            System.out.print(content);
        }
    }
    private static GenerationParam buildGenerationParam(Message userMsg) {
        return GenerationParam.builder()
                // If the environment variable is not configured, replace the following line with your Alibaba Cloud Model Studio API Key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("siliconflow/deepseek-v3.2")
                .enableThinking(true)
                .incrementalOutput(true)
                .resultFormat("message")
                .messages(Arrays.asList(userMsg))
                .build();
    }
    public static void streamCallWithMessage(Generation gen, Message userMsg)
            throws NoApiKeyException, ApiException, InputRequiredException {
        GenerationParam param = buildGenerationParam(userMsg);
        Flowable<GenerationResult> result = gen.streamCall(param);
        result.blockingForEach(message -> handleGenerationResult(message));
    }
    public static void main(String[] args) {
        try {
            Generation gen = new Generation();
            Message userMsg = Message.builder().role(Role.USER.getValue()).content("Who are you?").build();
            streamCallWithMessage(gen, userMsg);
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            System.err.println("An exception occurred: " + e.getMessage());
        }
    }
}

Response

====================Thinking Process====================

Hmm, the user asked a simple self-introduction question. This is a common question, so I need to quickly and clearly state my identity and function. I'll use a relaxed, friendly tone to introduce myself as DeepSeek-V3 and mention that I was created by DeepSeek. I can add the types of help I can provide, like answering questions, chatting, and tutoring, and finally use an emoji to add a touch of friendliness. No need to over-explain; keep it concise and clear.
====================Full Response====================

DeepSeek-V3, an intelligent assistant created by DeepSeek! I can help you answer various questions, provide advice, perform knowledge queries, and even chat with you! Whether it's for study, work, or questions about daily life, feel free to ask me. Is there anything I can help you with?

HTTP

Sample code

# China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
curl -X POST "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-H "X-DashScope-SSE: enable" \
-d '{
    "model": "siliconflow/deepseek-v3.2",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": "Who are you?"
            }
        ]
    },
    "parameters":{
        "enable_thinking": true,
        "incremental_output": true,
        "result_format": "message"
    }
}'