Alibaba Cloud Model Studio:Streaming output

from openai import OpenAI
import os

client = OpenAI(
    # API keys differ by region. Get your API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    # If you haven't configured an environment variable, replace the next line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-vl-plus",  # Replace with other multimodal models as needed and adjust 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 last chunk's choices field is an empty list and should be skipped (token usage can be obtained via 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 notes =======
# Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
# API keys differ by region. Get your API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# === Delete this comment before running ===

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.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
# Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.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(
    # API keys differ by region. Get your API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    # If you haven't configured an environment variable, replace the next line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model='qwen3-vl-plus',  #  Replace with other multimodal models as needed and adjust 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 {
        // Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.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()
                // API keys differ by region. Get your API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                // If you haven't configured an environment variable, replace the next line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")  //  Replace with other multimodal models as needed and adjust 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 notes =======
# API keys differ by region. Get your API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
# === Delete this comment before running ===

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.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
    }
}'

Example code

from openai import OpenAI
import os

# Initialize the OpenAI client
client = OpenAI(
    # If you haven't configured an environment variable, replace with your Alibaba Cloud Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

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

completion = client.chat.completions.create(
    model="qwen-plus",  # Replace with other deep-thinking models as needed
    messages=messages,
    # The enable_thinking parameter enables the thinking process. This parameter has no effect on models qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-thinking-2507, and QwQ.
    extra_body={"enable_thinking": True},
    stream=True,
    # stream_options={
    #     "include_usage": True
    # },
)

reasoning_content = ""  # Full thought process
answer_content = ""  # Full response
is_answering = False  # Whether in the response stage
print("\n" + "=" * 20 + "Thought process" + "=" * 20 + "\n")

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

    delta = chunk.choices[0].delta

    # Collect only 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

Response

====================Thought process====================

Okay, the user asked "Who are you," so I need to give an accurate and friendly answer. First, I should confirm my identity as Qwen, developed by Tongyi Lab under Alibaba Group. Next, explain my main functions, like answering questions, creating text, logical reasoning, etc. Keep the tone approachable and avoid overly technical terms so the user feels comfortable. Also, avoid complex jargon and ensure the answer is concise. Additionally, include some interactive elements to encourage further questions. Finally, check for any missing key information, such as my Chinese name "Tongyi Qianwen" and English name "Qwen," along with my company and lab. Make sure the response is comprehensive and meets user expectations.
====================Full response====================

Hello! I am Qwen, a large-scale language model independently developed by Tongyi Lab under Alibaba Group. I can answer questions, create text, perform logical reasoning, programming, and more, aiming to provide high-quality information and services. You can call me Qwen or simply Tongyi Qianwen. How can I help you?

Example 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 environment variable
    baseURL: 'https://{WorkspaceId}.ap-southeast-1.maas.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({
            // Replace with other Qwen3 models or QwQ models as needed
            model: 'qwen-plus',
            messages,
            stream: true,
            // The enable_thinking parameter enables the thinking process. This parameter has no effect on models qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-thinking-2507, and QwQ.
            enable_thinking: true
        });
        console.log('\n' + '='.repeat(20) + 'Thought 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 thinking content
            if (delta.reasoning_content !== undefined && delta.reasoning_content !== null) {
                if (!isAnswering) {
                    process.stdout.write(delta.reasoning_content);
                }
                reasoningContent += delta.reasoning_content;
            }

            // Received content, start responding
            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

====================Thought process====================

Okay, the user asked "Who are you," so I need to state my identity. First, I should clearly say I am Qwen, a large-scale language model developed by Alibaba Cloud. Next, mention my main functions, like answering questions, creating text, logical reasoning, etc. Also emphasize my multilingual support, including Chinese and English, so users know I can handle requests in different languages. Additionally, explain my application scenarios, such as helping with learning, work, and daily life. However, since the user's question is direct, detailed information might not be necessary—keep it concise. Also, ensure a friendly tone and invite further questions. Check for any missing key information, like my version or latest updates, but the user probably doesn't need that much detail. Finally, confirm the response is accurate and error-free.
====================Full response====================

I am Qwen, a large-scale language model independently developed by Tongyi Lab under Alibaba Group. I can handle various tasks like answering questions, creating text, logical reasoning, and programming, supporting multiple languages including Chinese and English. If you have any questions or need help, feel free to tell me anytime!

Example code

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.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
}'

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]

Example code

import os
from dashscope import Generation
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/"

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

completion = Generation.call(
    # If you haven't configured an environment variable, replace the next line with your Alibaba Cloud Model Studio API key: api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace with other deep-thinking models as needed
    model="qwen-plus",
    messages=messages,
    result_format="message", # Qwen3 open-source models only support "message"; for better experience, we recommend setting this to "message" for other models too.
    # Enable deep thinking. This parameter has no effect on models qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-thinking-2507, and QwQ.
    enable_thinking=True,
    stream=True,
    incremental_output=True, # Qwen3 open-source models only support true; for better experience, we recommend setting this to true for other models too.
)

# Define full thought process
reasoning_content = ""
# Define full response
answer_content = ""
# Determine if finished thinking and started responding
is_answering = False

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

for chunk in completion:
    # If both thought process and response are empty, skip
    if (
        chunk.output.choices[0].message.content == ""
        and chunk.output.choices[0].message.reasoning_content == ""
    ):
        pass
    else:
        # If currently in thinking stage
        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 currently in response stage
        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 full thought process and full response, uncomment the following lines and run
# print("=" * 20 + "Full thought process" + "=" * 20 + "\n")
# print(f"{reasoning_content}")
# print("=" * 20 + "Full response" + "=" * 20 + "\n")
# print(f"{answer_content}")

Response

====================Thought process====================
Okay, the user asked: "Who are you?" I need to answer this question. First, clarify my identity as Qwen, a large-scale language model developed by Alibaba Cloud. Next, explain my functions and purposes, like answering questions, creating text, logical reasoning, etc. Also, emphasize my goal of being a helpful assistant.

Keep the expression conversational, avoiding professional jargon or complex sentence structures. Add friendly phrases like "Hello there～" to make the conversation natural. Also, ensure accuracy and don't omit key points like my developer, main functions, and usage scenarios.

Consider possible follow-up questions from the user, such as specific application examples or technical details, so subtly hint at further inquiries in the response. For example, mention "Whether it's everyday questions or professional issues, I'll do my best to help," which is both comprehensive and open-ended.

Finally, check for fluency, repetition, or redundant information to keep the response concise. Maintain a balance between friendliness and professionalism so users feel both approachable and reliable.
====================Full response====================
Hello there～ I'm Qwen, a large-scale language model developed by Alibaba Cloud. I can answer questions, create text, perform logical reasoning, programming, and more, aiming to provide help and support. Whether it's everyday questions or professional issues, I'll do my best to help. How can I assist you?

Example 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://{WorkspaceId}.ap-southeast-1.maas.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("====================Thought 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 haven't configured an environment variable, replace the next line with your Alibaba Cloud 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 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);
    }
}

Response

====================Thought process====================
Okay, the user asked "Who are you?", so I need to answer based on previous settings. First, my role is Qwen, a large-scale language model under Alibaba Group. Keep it conversational and simple.

The user might be new to me or confirming my identity. Start by directly stating who I am, then briefly explain my functions and purposes, like answering questions, creating text, programming, etc. Also mention multilingual support so users know I handle different languages.

Also, per guidelines, maintain human-like qualities, so use a friendly tone, maybe add emojis for warmth. Guide users to ask further questions or use my features, like asking what they need help with.

Avoid complex terms and keep it concise. Check for missing key points like multilingual support and specific capabilities. Ensure the response meets all requirements, including conversational style and simplicity.
====================Full response====================
Hello! I'm Qwen, a large-scale language model under Alibaba Group. I can answer questions, create text like stories, official documents, emails, scripts, perform logical reasoning, programming, express opinions, play games, and more. I'm proficient in multiple languages, including but not limited to Chinese, English, German, French, and Spanish. How can I help you?

Example code

# ======= Important notes =======
# API keys differ by region. Get your API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
# === Delete this comment before running ===
curl -X POST "https://{WorkspaceId}.ap-southeast-1.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": "qwen-plus",
    "input":{
        "messages":[      
            {
                "role": "user",
                "content": "Who are you?"
            }
        ]
    },
    "parameters":{
        "enable_thinking": true,
        "incremental_output": true,
        "result_format": "message"
    }
}'

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":"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":"asked","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":"welcome","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":"anytime","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":"tell","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":"me","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":"null"}]},"usage":{"total_tokens":378,"input_tokens":11,"output_tokens":367},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:365
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"}