How to use the code interpreter in the Qwen API - Alibaba Cloud Model Studio

Built-in Python code interpreter allows the model to write and run Python code in a sandbox to solve complex problems, such as mathematical calculations and data analytics.

Usage

Pass enable_code_interpreter: true in your API request.

The following examples show the core code for API calls using the OpenAI-compatible and DashScope Python SDK:

OpenAI compatible

# Import dependencies and create a client...
completion = client.chat.completions.create(
    # Use a model that supports the code interpreter
    model="qwen3-max-preview",
    messages=[{"role": "user", "content": "What is 123 to the power of 21?"}],
    # Because enable_code_interpreter is not a standard OpenAI parameter, you must pass it through extra_body when using the Python SDK. When using the Node.js SDK, pass it as a top-level parameter.
    extra_body={
        "enable_code_interpreter": True,
        # The code interpreter feature only supports calls in thinking mode
        "enable_thinking": True,
    },
    # The code interpreter feature only supports streaming output calls
    stream=True
)

The OpenAI-compatible protocol does not return the code run by the interpreter.

DashScope

# Import dependencies...
response = dashscope.Generation.call(
    # If you have not configured environment variables, replace the next line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-max-preview",
    messages=[{"role": "user", "content": "What is 123 to the power of 21?"}],
    # Enable the code interpreter using the enable_code_interpreter parameter
    enable_code_interpreter=True,
    # The code interpreter feature only supports thinking mode
    enable_thinking=True,
    result_format="message",
    # The code interpreter feature only supports streaming output calls
    stream=True
)

The code that the interpreter runs is returned in the tool_info field.

The model processes the request in stages:

Thinking: The model analyzes the user request and generates ideas and steps to solve the problem, returned in the reasoning_content.
Code execution: The model generates and executes Python code, returned in the tool_info. The OpenAI-compatible protocol does not support tool_info.
Result integration: The model receives the code execution result and plans the final response, returned in the reasoning_content.
Response: The model generates a natural language response, returned in the content.

Availability

Regions: Supported only in the China (Beijing) region. Use an API key from the China (Beijing) region.
Models: Supported only for the qwen3-max-preview model in thinking mode.

Getting started

The following examples show how the code interpreter efficiently solves mathematical calculation problems.

DashScope

The Java SDK is not supported.

Python

import os
import dashscope

messages = [
    {"role": "user", "content": "What is 123 to the power of 21?"},
]

response = dashscope.Generation.call(
    # If you have not configured environment variables, replace the next line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-max-preview",
    messages=messages,
    enable_code_interpreter=True,
    enable_thinking=True,
    result_format="message",
    # Only streaming output is supported
    stream=True
)

for chunk in response:
    output = chunk["output"]
    print(output)

Response example

{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": "The"}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " user is asking"}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " me"}}]}
...
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " I'll write a"}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " simple Python program to calculate"}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": ""}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": ""}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": ""}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": ""}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": ""}}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": "The"}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " user"}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " asked"}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
...
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " I should present this result"}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " to the user in"}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "", "reasoning_content": " a clear format."}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "123 to the power of ", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "21 is:\n\n", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "772693", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "644665", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "498656", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "530734", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "733880", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "300615", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "222117", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "null", "message": {"role": "assistant", "content": "23", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}
{"text": null, "finish_reason": null, "choices": [{"finish_reason": "stop", "message": {"role": "assistant", "content": "", "reasoning_content": ""}}], "tool_info": [{"code_interpreter": {"code": "123**21"}, "type": "code_interpreter"}]}

curl

curl -X POST https://dashscope.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": "qwen3-max-preview",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": "What is 123 to the power of 21?"
            }
        ]
    },
    "parameters": {
        "enable_code_interpreter": true,
        "enable_thinking": true,
        "result_format": "message"
    }
}'

Response example

<...Text content...> is an explanatory comment that identifies the processing stage and is not part of the actual API response.

id:1
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"The","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":290,"output_tokens":3,"input_tokens":287,"output_tokens_details":{"reasoning_tokens":1}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

id:2
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" user is asking","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":293,"output_tokens":6,"input_tokens":287,"output_tokens_details":{"reasoning_tokens":4}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

...Thinking stage...

id:21
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":388,"output_tokens":101,"input_tokens":287,"output_tokens_details":{"reasoning_tokens":68}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

...Thinking ends, code interpreter starts...

id:22
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"","role":"assistant"},"finish_reason":"null"}],"tool_info":[{"code_interpreter":{"code":"123**21"},"type":"code_interpreter"}]},"usage":{"total_tokens":388,"output_tokens":101,"input_tokens":287,"output_tokens_details":{"reasoning_tokens":68},"plugins":{"code_interpreter":{"count":1}}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

...Thinking starts after code interpreter runs...

id:23
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"The","role":"assistant"},"finish_reason":"null"}],"tool_info":[{"code_interpreter":{"code":"123**21"},"type":"code_interpreter"}]},"usage":{"total_tokens":838,"output_tokens":104,"input_tokens":734,"output_tokens_details":{"reasoning_tokens":69},"plugins":{"code_interpreter":{"count":1}}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

id:24
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" user","role":"assistant"},"finish_reason":"null"}],"tool_info":[{"code_interpreter":{"code":"123**21"},"type":"code_interpreter"}]},"usage":{"total_tokens":839,"output_tokens":105,"input_tokens":734,"output_tokens_details":{"reasoning_tokens":70},"plugins":{"code_interpreter":{"count":1}}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

...Thinking stage...

id:43
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" a clear format.","role":"assistant"},"finish_reason":"null"}],"tool_info":[{"code_interpreter":{"code":"123**21"},"type":"code_interpreter"}]},"usage":{"total_tokens":942,"output_tokens":208,"input_tokens":734,"output_tokens_details":{"reasoning_tokens":171},"plugins":{"code_interpreter":{"count":1}}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

...Thinking ends, response starts...

id:44
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"123 to the power of ","reasoning_content":"","role":"assistant"},"finish_reason":"null"}],"tool_info":[{"code_interpreter":{"code":"123**21"},"type":"code_interpreter"}]},"usage":{"total_tokens":947,"output_tokens":213,"input_tokens":734,"output_tokens_details":{"reasoning_tokens":171},"plugins":{"code_interpreter":{"count":1}}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

...

id:53
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"23","reasoning_content":"","role":"assistant"},"finish_reason":"null"}],"tool_info":[{"code_interpreter":{"code":"123**21"},"type":"code_interpreter"}]},"usage":{"total_tokens":997,"output_tokens":263,"input_tokens":734,"output_tokens_details":{"reasoning_tokens":171},"plugins":{"code_interpreter":{"count":1}}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

id:54
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"","role":"assistant"},"finish_reason":"stop"}],"tool_info":[{"code_interpreter":{"code":"123**21"},"type":"code_interpreter"}]},"usage":{"total_tokens":997,"output_tokens":263,"input_tokens":734,"output_tokens_details":{"reasoning_tokens":171},"plugins":{"code_interpreter":{"count":1}}},"request_id":"a1959ad1-2637-4672-a21f-4d351371d254"}

OpenAI compatible

Python

from openai import OpenAI
import os

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

messages = [{"role": "user", "content": "What is 123 to the power of 21?"}]

completion = client.chat.completions.create(
    model="qwen3-max-preview",
    messages=messages,
    extra_body={"enable_thinking": True, "enable_code_interpreter": True},
    stream=True,
    stream_options={
        "include_usage": True
    },
)

reasoning_content = ""  # Complete thinking process
answer_content = ""  # Complete response
is_answering = False  # Flag to check if the response stage 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

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

Response example

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

The user is asking for 123 to the power of 21. This is a math problem. I need to calculate 123^21.

I can use the code calculator to compute this value. I need to call the code_interpreter function and pass the Python code to calculate 123**21.

Let me construct this function call.
The user asked for 123 to the power of 21, and I used Python code to calculate the result. The calculation shows that 123 to the power of 21 equals 77269364466549865653073473388030061522211723. This is a very large number. I should provide this directly
====================Complete response====================

123 to the power of 21 is: 77269364466549865653073473388030061522211723
Usage:
CompletionUsage(completion_tokens=245, prompt_tokens=719, total_tokens=964, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=None, audio_tokens=None, reasoning_tokens=153, rejected_prediction_tokens=None), prompt_tokens_details=None)

Node.js

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 variables
    // The following is the base_url for the Beijing region. If you use a model in the Singapore region, replace the base_url with: https://dashscope-intl.aliyuncs.com/compatible-mode/v1
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

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

async function main() {
    try {
        const messages = [{ role: 'user', content: 'What is 123 to the power of 21?' }];
        const stream = await openai.chat.completions.create({
            model: 'qwen3-max-preview',
            messages,
            stream: true,
            enable_thinking: true,
            enable_code_interpreter: 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;
            }

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

main();

Response example

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

The user is asking for the value of 123 raised to the power of 21. This is a mathematical calculation that I can perform using Python's code interpreter. I'll use the exponentiation operator ** to calculate this.

Let me write the code to compute 123**21.The calculation has been completed successfully. The result of 123 raised to the power of 21 is a very large number: 77269364466549865653073473388030061522211723.

I should present this result clearly to the user.

====================Complete response====================

123 to the power of 21 is: 77269364466549865653073473388030061522211723

curl

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3-max-preview",
    "messages": [
        {
            "role": "user", 
            "content": "What is 123 to the power of 21?"
        }
    ],
    "enable_code_interpreter": true,
    "enable_thinking": true,
    "stream": true
}'

Response example

data: {"choices":[{"delta":{"content":null,"role":"assistant","reasoning_content":""},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1761899724,"system_fingerprint":null,"model":"qwen3-max-preview","id":"chatcmpl-2f96ef0b-5924-4dfc-b768-4d53ec538b4e"}

data: {"choices":[{"finish_reason":null,"logprobs":null,"delta":{"content":null,"reasoning_content":"The user"},"index":0}],"object":"chat.completion.chunk","usage":null,"created":1761899724,"system_fingerprint":null,"model":"qwen3-max-preview","id":"chatcmpl-2f96ef0b-5924-4dfc-b768-4d53ec538b4e"}

data: {"choices":[{"delta":{"content":null,"reasoning_content":" is asking"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1761899724,"system_fingerprint":null,"model":"qwen3-max-preview","id":"chatcmpl-2f96ef0b-5924-4dfc-b768-4d53ec538b4e"}

data: {"choices":[{"delta":{"content":null,"reasoning_content":" for"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1761899724,"system_fingerprint":null,"model":"qwen3-max-preview","id":"chatcmpl-2f96ef0b-5924-4dfc-b768-4d53ec538b4e"}

...

data: {"choices":[{"delta":{"content":"a very large number, with a total","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1761899724,"system_fingerprint":null,"model":"qwen3-max-preview","id":"chatcmpl-2f96ef0b-5924-4dfc-b768-4d53ec538b4e"}

data: {"choices":[{"delta":{"content":" of 43 digits","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1761899724,"system_fingerprint":null,"model":"qwen3-max-preview","id":"chatcmpl-2f96ef0b-5924-4dfc-b768-4d53ec538b4e"}

data: {"choices":[{"delta":{"content":".","reasoning_content":null},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1761899724,"system_fingerprint":null,"model":"qwen3-max-preview","id":"chatcmpl-2f96ef0b-5924-4dfc-b768-4d53ec538b4e"}

data: {"choices":[{"finish_reason":"stop","delta":{"content":"","reasoning_content":null},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1761899724,"system_fingerprint":null,"model":"qwen3-max-preview","id":"chatcmpl-2f96ef0b-5924-4dfc-b768-4d53ec538b4e"}

data: [DONE]

Response parsing

The following DashScope Python SDK example shows how to perform two calculations in a single request. Then, it returns the code and the total number of calls.

The OpenAI-compatible protocol does not return data during the code execution stage, which creates a response gap between the thinking and result integration stages. Because both of these stages return content in reasoning_content, you can process them together as the thinking stage. For a response parsing example, see the code in the Getting started section.

import os  
from dashscope import Generation  

messages = [{"role": "user", "content": "Run the code interpreter twice: first, calculate the value of 123 to the power of 23, and second, divide the result by 5"}]  

response = Generation.call(  
    api_key=os.getenv("DASHSCOPE_API_KEY"),  
    model="qwen3-max-preview",  
    messages=messages,  
    result_format="message",
    enable_thinking=True,
    enable_code_interpreter=True,
    stream=True,
    incremental_output=True,
)  

# Status flags: track if tool info is printed, if the answering stage has started, and if in the reasoning section
is_answering = False  
in_reasoning_section = False  
cur_tools = []

# Print a separated area with a title
def print_section(title):  
    print(f"\n{'=' * 20}{title}{'=' * 20}")  

# Initially print the "Thinking process" title
print_section("Thinking process")  
in_reasoning_section = True  

# Process each data block returned by the model in a stream
for chunk in response:  
    try:  
        # Extract key fields from the response: content, reasoning text, tool call information
        choice = chunk.output.choices[0]  
        msg = choice.message  
        content = msg.get("content", "")            # Final answer content
        reasoning = msg.get("reasoning_content", "") # Reasoning process text
        tools = chunk.output.get("tool_info", None)  # Tool call information
    except (IndexError, AttributeError, KeyError):
        # Skip data blocks with abnormal structures
        continue  
    # If there is no valid content, skip the current block
    if not content and not reasoning and tools is None:  
        continue  
    # Output the reasoning process
    if reasoning and not is_answering:  
        if not in_reasoning_section:  
            print_section("Thinking process")  
            in_reasoning_section = True  
        print(reasoning, end="", flush=True)  
    if tools is not None and tools != cur_tools:  
        print_section("Tool information")  
        print(tools)  
        in_reasoning_section = False  
        cur_tools = tools
    # Output the final answer content
    if content:  
        if not is_answering:  
            print_section("Complete response")  
            is_answering = True  
            in_reasoning_section = False  
        print(content, end="", flush=True)  
# Print the number of code interpreter calls
print_section("Code interpreter run count")  
print(chunk.usage.plugins)

Response example

====================Thinking process====================
The user wants to run the code interpreter twice:
1. First run: Calculate 123 to the power of 23
2. Second run: Divide the result of the first run by 5

I need to first call the code interpreter to calculate 123**23, and then use this result to call the code interpreter again to divide by 5.

Let me do the first calculation.

====================Tool information====================
[{'code_interpreter': {'code': '123**23'}, 'type': 'code_interpreter'}]

====================Thinking process====================
The first calculation got the value of 123 to the power of 23: 1169008215014432917465348578887506800769541157267

Now for the second run, I need to divide this result by 5. I need to use this exact value for the division
====================Tool information====================
[{'code_interpreter': {'code': '123**23'}, 'type': 'code_interpreter'}, {'code_interpreter': {'code': ''}, 'type': 'code_interpreter'}]

====================Tool information====================
[{'code_interpreter': {'code': '123**23'}, 'type': 'code_interpreter'}, {'code_interpreter': {'code': '1169008215014432917465348578887506800769541157267 / 5'}, 'type': 'code_interpreter'}]

====================Thinking process====================
The user requested to run the code interpreter twice:
1. First, calculate 123 to the power of 23, the result is: 1169008215014432917465348578887506800769541157267
2. Second, divide this result by 5, which gives: 2.338016430028866e+47

Now I need to report these two to the user
====================Complete response====================
First run result: 123 to the power of 23 = 1169008215014432917465348578887506800769541157267

Second run result: The above result divided by 5 = 2.338016430028866e+47
====================Code interpreter run count====================
{'code_interpreter': {'count': 2}}

Notes

Code interpreter and function calling are mutually exclusive. You cannot enable them at the same time.
Otherwise, an error will occur.
After you enable the code interpreter, a single request triggers multiple model inferences. The usage field summarizes the token consumption for all calls.

Billing

There is no extra charge for the code interpreter, but it increases token consumption.