U2 - Unisound

Python

Sample code

from openai import OpenAI
import os

# Initialize the OpenAI client
client = OpenAI(
    # If you have not configured the environment variable, replace with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the China (Beijing) region. Replace {WorkspaceId} with your Model Studio workspace ID. The URL varies by region.
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)

messages = [{"role": "user", "content": "Which is larger, 9.9 or 9.11?"}]
completion = client.chat.completions.create(
    model="unisound/unisound-u2",
    messages=messages,
    stream=True,
    stream_options={
        "include_usage": True
    },
    # unisound-u2 runs in thinking mode by default. To disable it, set "thinking": {"type": "disabled"}
    extra_body={
        "thinking": {"type": "enabled"},
        "reasoning_effort": "xhigh"
    }
)

reasoning_content = ""  # Full chain-of-thought
answer_content = ""  # Full response
is_answering = False  # Whether the response phase has started
print("\n" + "=" * 20 + "Chain-of-thought" + "=" * 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

    # Content received. The response phase starts.
    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

====================Chain-of-thought====================

The user wants to compare 9.9 and 9.11.
Align the decimal places: 9.9 = 9.90, and 9.11 = 9.11.
Compare the decimal parts: 0.90 > 0.11, so 9.9 is larger.
====================Full response====================

9.9 is larger.

Align the decimal places before comparing: 9.9 = 9.90, and 9.11 = 9.11. Because 0.90 > 0.11, 9.9 > 9.11.
====================Token usage====================

CompletionUsage(completion_tokens=96, prompt_tokens=10, total_tokens=106, prompt_tokens_details={'cached_tokens': 0})

Node.js

Sample code

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

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

let reasoningContent = ''; // Full chain-of-thought
let answerContent = ''; // Full response
let isAnswering = false; // Whether the response phase has started

async function main() {
    try {
        const messages = [{ role: 'user', content: 'Which is larger, 9.9 or 9.11?' }];

        const stream = await openai.chat.completions.create({
            model: 'unisound/unisound-u2',
            messages,
            stream: true,
            stream_options: {
                include_usage: true
            },
            // unisound-u2 runs in thinking mode by default. To disable it, set thinking: { type: 'disabled' }
            thinking: { type: 'enabled' },
            reasoning_effort: 'xhigh'
        });

        console.log('\n' + '='.repeat(20) + 'Chain-of-thought' + '='.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;
            }

            // Content received. The response phase starts.
            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

====================Chain-of-thought====================

The user wants to compare 9.9 and 9.11.
Align the decimal places: 9.9 = 9.90, and 9.11 = 9.11.
Compare the decimal parts: 0.90 > 0.11, so 9.9 is larger.
====================Full response====================

9.9 is larger.

Align the decimal places before comparing: 9.9 = 9.90, and 9.11 = 9.11. Because 0.90 > 0.11, 9.9 > 9.11.
====================Token usage====================

{ prompt_tokens: 10, completion_tokens: 96, total_tokens: 106, prompt_tokens_details: { cached_tokens: 0 } }

HTTP

Sample code

# The following URL is for the China (Beijing) region. Replace {WorkspaceId} with your Model Studio workspace ID. The URL varies 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": "unisound/unisound-u2",
    "messages": [
        {
            "role": "user",
            "content": "Which is larger, 9.9 or 9.11?"
        }
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    },
    "thinking": {
        "type": "enabled"
    },
    "reasoning_effort": "xhigh"
}'