Alibaba Cloud Model Studio:Streaming

from openai import OpenAI
import os

client = OpenAI(
    # The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the base URL for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-vl-plus",  # You can replace this with other multimodal models and modify the messages accordingly.
    messages=[
        {"role": "user",
        "content": [{"type": "image_url",
                    "image_url": {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},},
                    {"type": "text", "text": "What scene is depicted in the image?"}]}],
    stream=True,
  # stream_options={"include_usage": True}
)
full_content = ""
print("Streaming output content:")
for chunk in completion:
    # If stream_options.include_usage is True, the choices field of the last chunk is an empty list and should be skipped. You can get the token usage from chunk.usage.
    if chunk.choices and chunk.choices[0].delta.content != "":
        full_content += chunk.choices[0].delta.content
        print(chunk.choices[0].delta.content)
print(f"Full content: {full_content}")

# ======= Important =======
# The following is the base URL for the Singapore region. If you use a model in the China (Beijing) region, replace the base URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl --location 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3-vl-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "What scene is depicted in the image?"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true}
}'

import os
from dashscope import MultiModalConversation
import dashscope
# The following is the base URL for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
            {"text": "What scene is depicted in the image?"}
        ]
    }
]

responses = MultiModalConversation.call(
    # The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model='qwen3-vl-plus',  #  You can replace this with other multimodal models and modify the messages accordingly.
    messages=messages,
    stream=True,
    incremental_output=True)
    
full_content = ""
print("Streaming output content:")
for response in responses:
    if response["output"]["choices"][0]["message"].content:
        print(response.output.choices[0].message.content[0]['text'])
        full_content += response.output.choices[0].message.content[0]['text']
print(f"Full content: {full_content}")

import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Map;

import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import io.reactivex.Flowable;
import com.alibaba.dashscope.utils.Constants;

public class Main {
    static {
        // The following is the base URL for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    public static void streamCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        // must create mutable map.
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "What scene is depicted in the image?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")  //  You can replace this with other multimodal models and modify the messages accordingly.
                .messages(Arrays.asList(userMessage))
                .incrementalOutput(true)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(item -> {
            try {
                List<Map<String, Object>> content = item.getOutput().getChoices().get(0).getMessage().getContent();
                    // Check if content exists and is not empty.
                if (content != null &&  !content.isEmpty()) {
                    System.out.println(content.get(0).get("text"));
                    }
            } catch (Exception e){
                System.exit(0);
            }
        });
    }

    public static void main(String[] args) {
        try {
            streamCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

# ======= Important =======
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the base URL for the Singapore region. If you use a model in the China (Beijing) region, replace the base URL with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-H 'X-DashScope-SSE: enable' \
-d '{
    "model": "qwen3-vl-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                    {"text": "What scene is depicted in the image?"}
                ]
            }
        ]
    },
    "parameters": {
        "incremental_output": true
    }
}'

Sample code

from openai import OpenAI
import os

# Initialize the OpenAI client.
client = OpenAI(
    # If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

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

completion = client.chat.completions.create(
    model="qwen-plus",  # You can replace this with other deep thinking models as needed.
    messages=messages,
    # The enable_thinking parameter enables the thinking process. This parameter is not supported for the qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-thinking-2507, and QwQ models.
    extra_body={"enable_thinking": True},
    stream=True,
    # stream_options={
    #     "include_usage": True
    # },
)

reasoning_content = ""  # Full thinking process
answer_content = ""  # Full response
is_answering = False  # Whether the responding phase has started
print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")

for chunk in completion:
    if not chunk.choices:
        print("\nUsage:")
        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

    # Received content, start responding.
    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

Sample response

====================Thinking process====================

Okay, the user is asking "Who are you?". I need to provide an accurate and friendly answer. First, I must confirm my identity: Qwen, developed by the Tongyi Lab at Alibaba Group. Next, I should explain my main functions, such as answering questions, creating text, and logical reasoning. I need to maintain a friendly tone and avoid being too technical to make the user feel at ease. I should also avoid complex jargon to keep the answer simple and clear. Additionally, I might add some interactive elements, inviting the user to ask more questions to encourage further conversation. Finally, I'll check if I've missed any important information, such as my Chinese name "Tongyi Qianwen" and English name "Qwen", and my parent company and lab. I need to ensure the answer is comprehensive and meets the user's expectations.
====================Full response====================

Hello! I am Qwen, a large-scale language model developed by the Tongyi Lab at Alibaba Group. I can answer questions, create text, perform logical reasoning, write code, and more, all to provide users with high-quality information and services. You can call me Qwen, or just Tongyi Qianwen. How can I help you?

Sample code

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

// Initialize the OpenAI client.
const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY, // Read from an environment variable
    baseURL: 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1'
});

let reasoningContent = '';
let answerContent = '';
let isAnswering = false;

async function main() {
    try {
        const messages = [{ role: 'user', content: 'Who are you?' }];
        const stream = await openai.chat.completions.create({
            // You can replace this with other Qwen3 or QwQ models as needed.
            model: 'qwen-plus',
            messages,
            stream: true,
            // The enable_thinking parameter enables the thinking process. This parameter is not supported for the qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-thinking-2507, and QwQ models.
            enable_thinking: true
        });
        console.log('\n' + '='.repeat(20) + 'Thinking process' + '='.repeat(20) + '\n');

        for await (const chunk of stream) {
            if (!chunk.choices?.length) {
                console.log('\nUsage:');
                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;
            }

            // Start replying after content is received.
            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();

Sample response

====================Thinking process====================

Okay, the user is asking "Who are you?". I need to answer with my identity. First, I should clearly state that I am Qwen, a large-scale language model developed by Alibaba Cloud. Next, I can mention my main functions, such as answering questions, creating text, and logical reasoning. I should also emphasize my multilingual support, including Chinese and English, so the user knows I can handle requests in different languages. Additionally, I might need to explain my application scenarios, such as helping with study, work, and daily life. However, the user's question is quite direct, so I should keep it concise. I also need to ensure a friendly tone and invite the user to ask further questions. I will check for any missing important information, such as my version or latest updates, but the user probably doesn't need that level of detail. Finally, I will confirm the answer is accurate and free of errors.
====================Full response====================

I am Qwen, a large-scale language model developed by the Tongyi Lab at Alibaba Group. I can perform various tasks such as answering questions, creating text, logical reasoning, and coding. I support multiple languages, including Chinese and English. If you have any questions or need help, feel free to let me know!

Sample code

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen-plus",
    "messages": [
        {
            "role": "user", 
            "content": "Who are you?"
        }
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    },
    "enable_thinking": true
}'

Sample response

data: {"choices":[{"delta":{"content":null,"role":"assistant","reasoning_content":""},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1745485391,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-e2edaf2c-8aaf-9e54-90e2-b21dd5045503"}

.....

data: {"choices":[{"finish_reason":"stop","delta":{"content":"","reasoning_content":null},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1745485391,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-e2edaf2c-8aaf-9e54-90e2-b21dd5045503"}

data: {"choices":[],"object":"chat.completion.chunk","usage":{"prompt_tokens":10,"completion_tokens":360,"total_tokens":370},"created":1745485391,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-e2edaf2c-8aaf-9e54-90e2-b21dd5045503"}

data: [DONE]

Sample code

import os
from dashscope import Generation
import dashscope
dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1/"

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

completion = Generation.call(
    # If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # You can replace this with other deep thinking models as needed.
    model="qwen-plus",
    messages=messages,
    result_format="message", # Open-source Qwen3 models only support "message". For a better experience, we recommend you set this parameter to "message" for other models as well.
    # Enable deep thinking. This parameter has no effect on the qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-thinking-2507, and QwQ models.
    enable_thinking=True,
    stream=True,
    incremental_output=True, # Open-source Qwen3 models only support true. For a better experience, we recommend you set this parameter to true for other models as well.
)

# Define the complete thinking process.
reasoning_content = ""
# Define the complete response.
answer_content = ""
# Determine whether the thinking process is complete and the response is being generated.
is_answering = False

print("=" * 20 + "Thinking process" + "=" * 20)

for chunk in completion:
    # If both the thinking process and the response are empty, do nothing.
    if (
        chunk.output.choices[0].message.content == ""
        and chunk.output.choices[0].message.reasoning_content == ""
    ):
        pass
    else:
        # If the current part is the thinking process.
        if (
            chunk.output.choices[0].message.reasoning_content != ""
            and chunk.output.choices[0].message.content == ""
        ):
            print(chunk.output.choices[0].message.reasoning_content, end="", flush=True)
            reasoning_content += chunk.output.choices[0].message.reasoning_content
        # If the current part is the response.
        elif chunk.output.choices[0].message.content != "":
            if not is_answering:
                print("\n" + "=" * 20 + "Full response" + "=" * 20)
                is_answering = True
            print(chunk.output.choices[0].message.content, end="", flush=True)
            answer_content += chunk.output.choices[0].message.content

# To print the complete thinking process and response, uncomment and run the following code.
# print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
# print(f"{reasoning_content}")
# print("=" * 20 + "Full response" + "=" * 20 + "\n")
# print(f"{answer_content}")

Sample response

====================Thinking process====================
Okay, the user is asking, "Who are you?" I need to answer this question. First, I must clarify my identity: Qwen, a large-scale language model developed by Alibaba Cloud. Next, I should explain my functions and purposes, such as answering questions, creating text, and logical reasoning. I should also emphasize my goal of being a helpful assistant to users, providing help and support.

When responding, I should maintain a conversational tone and avoid using technical jargon or complex sentence structures. I can use friendly expressions, like "Hello there! ~", to make the conversation more natural. I also need to ensure the information is accurate and does not omit key points, such as my developer, main functions, and application scenarios.

I should also consider potential follow-up questions from the user, such as specific application examples or technical details. So, I can subtly set up opportunities in my answer to guide the user to ask more questions. For example, by mentioning, "Whether it's a question about daily life or a professional field, I can do my best to help," which is both comprehensive and open-ended.

Finally, I will check if the response is fluent, without repetition or redundancy, ensuring it is concise and clear. I will also maintain a balance between being friendly and professional, so the user feels that I am both approachable and reliable.
====================Full response====================
Hello there! ~ I am Qwen, a large-scale language model developed by Alibaba Cloud. I can answer questions, create text, perform logical reasoning, write code, and more, all to provide help and support to users. Whether it's a question about daily life or a professional field, I can do my best to help. How can I assist you?

Sample code

// dashscope SDK version >= 2.19.4
import java.util.Arrays;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
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 com.alibaba.dashscope.utils.Constants;

public class Main {
    static {
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    private static final Logger logger = LoggerFactory.getLogger(Main.class);
    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.isEmpty()) {
            reasoningContent.append(reasoning);
            if (isFirstPrint) {
                System.out.println("====================Thinking process====================");
                isFirstPrint = false;
            }
            System.out.print(reasoning);
        }

        if (!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 you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-plus")
                .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);
//             Print the final result.
//            if (reasoningContent.length() > 0) {
//                System.out.println("\n====================Full response====================");
//                System.out.println(finalContent.toString());
//            }
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            logger.error("An exception occurred: {}", e.getMessage());
        }
        System.exit(0);
    }
}

Result

====================Thinking process====================
Okay, the user is asking "Who are you?". I need to answer based on my previous settings. First, my role is Qwen, a large-scale language model from Alibaba Group. I need to keep my language conversational, simple, and easy to understand.

The user might be new to me or wants to confirm my identity. I should first directly answer who I am, then briefly explain my functions and uses, such as answering questions, creating text, and coding. I also need to mention my multilingual support so the user knows I can handle requests in different languages.

Also, according to the guidelines, I need to maintain a human-like personality, so my tone should be friendly, and I might use emojis to add a touch of warmth. I might also need to guide the user to ask further questions or use my functions, for example, by asking them what they need help with.

I need to be careful not to use complex jargon and avoid being long-winded. I will check for any missed key points, such as multilingual support and specific capabilities. I will ensure the answer meets all requirements, including being conversational and concise.
====================Full response====================
Hello! I am Qwen, a large-scale language model from Alibaba Group. I can answer questions, create text such as stories, official documents, emails, and scripts, perform logical reasoning, write code, express opinions, and play games. I am proficient in multiple languages, including but not limited to Chinese, English, German, French, and Spanish. Is there anything I can help you with?

Sample code

# ======= Important =======
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation
# === Delete this comment before execution ===

curl -X POST "https://dashscope-intl.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": "qwen-plus",
    "input":{
        "messages":[      
            {
                "role": "user",
                "content": "Who are you?"
            }
        ]
    },
    "parameters":{
        "enable_thinking": true,
        "incremental_output": true,
        "result_format": "message"
    }
}'

Sample response

id:1
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"Hmm","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":14,"input_tokens":11,"output_tokens":3},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:2
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":",","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":15,"input_tokens":11,"output_tokens":4},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:3
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" the user","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":16,"input_tokens":11,"output_tokens":5},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:4
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" is asking","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":17,"input_tokens":11,"output_tokens":6},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:5
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" '","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":18,"input_tokens":11,"output_tokens":7},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}
......

id:358
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":" help","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":373,"input_tokens":11,"output_tokens":362},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:359
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":",","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":374,"input_tokens":11,"output_tokens":363},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:360
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":" feel free to","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":375,"input_tokens":11,"output_tokens":364},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:361
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":" let me","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":376,"input_tokens":11,"output_tokens":365},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:362
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":" know","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":377,"input_tokens":11,"output_tokens":366},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:363
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"!","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":378,"input_tokens":11,"output_tokens":367},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:364
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"","role":"assistant"},"finish_reason":"stop"}]},"usage":{"total_tokens":378,"input_tokens":11,"output_tokens":367},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}