Ling-AntDigital

Updated at:

This document describes how to call the Ling series model inference service directly provided by AntDigital on the Alibaba Cloud Model Studio platform.

ImportantThe features described in this topic are available only in the China (Beijing) region. To call the model, you must obtain and configure an API key in the China (Beijing) region.

Activate the service

  1. Go to the Model Studio console, search for Ling, find the antdigital/Ling-3.1-flash model card, and click Activate Now.
  2. In the pop-up window, confirm the activation and authorization.

After you complete these steps, you can call the AntDigital Ling model service.

Getting started

Prerequisites

antdigital/Ling-3.1-flash is a hybrid thinking model directly provided by AntDigital. It supports only text input and runs in thinking mode by default:

  • Thinking mode (default, or enable_thinking: true): The model outputs its reasoning process (reasoning_content).
  • Non-thinking mode (enable_thinking: false): The model directly outputs the result without the reasoning process.

You can use the preserve_thinking parameter to pass the thinking process in multi-turn conversations. For more information, see Multi-turn conversation.

The following example calls antdigital/Ling-3.1-flash in thinking mode with streaming output.

Note

  • enable_thinking is not a standard OpenAI parameter. In the OpenAI Python SDK, pass it via extra_body. In the Node.js SDK, pass it as a top-level parameter.
  • For streaming output, include_usage in stream_options supports only true. Passing false returns an error.

Python

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"),
    # The following URL is for the China (Beijing) region. Replace {WorkspaceId} with your Model Studio workspace ID. URLs vary 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="antdigital/Ling-3.1-flash",
    messages=messages,
    stream=True,
    stream_options={
        "include_usage": True
    },
    # Thinking mode is enabled by default. To disable it, set enable_thinking to False
    extra_body={"enable_thinking": True}
)

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

    # 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

Node.js

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

// Initialize the OpenAI client
const openai = new OpenAI({
    // If you have not configured an environment variable, replace the following line 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. URLs vary 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: 'antdigital/Ling-3.1-flash',
            messages,
            stream: true,
            stream_options: {
                include_usage: true
            },
            // Thinking mode is enabled by default. To disable it, set enable_thinking to false
            enable_thinking: true
        });

        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;
            }

            // 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();

curl

# The following URL is for the China (Beijing) region. Replace {WorkspaceId} with your Model Studio 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": "antdigital/Ling-3.1-flash",
    "messages": [
        {
            "role": "user",
            "content": "Which is larger, 9.9 or 9.11?"
        }
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    },
    "enable_thinking": true
}'

Other features

FeatureSupportedNotes
Multi-turn conversationSupported—
Function callingSupportedSupports streaming tool call arguments through tool_stream. Does not support parallel_tool_calls
Partial modeSupported—
Context cacheSupportedImplicit cache. Input tokens that hit the cache are billed at 20% of the input price
Structured outputSupportedresponse_format supports only {"type": "json_object"}. json_schema is not supported
Web searchUnsupported—
Multimodal inputUnsupportedSupports only text input

antdigital/Ling-3.1-flash does not support the following parameters: thinking_budget, reasoning_effort, parallel_tool_calls, seed, logprobs, top_logprobs, enable_code_interpreter, enable_search, search_options, and skill.

Models and pricing

ModelDescription
antdigital/Ling-3.1-flashHybrid thinking model with thinking mode enabled by default. Context length: 1,048,576 tokens

For model pricing and rate limits, see Model pricing and Rate limits.

You are charged based on the input and output tokens of the model.

In thinking mode, the chain-of-thought is billed as output tokens.

Error codes

If a model call fails and returns an error message, see Error codes for troubleshooting.