GLM-5.1 API 사용법: 코드 예제 완벽 가이드

export BIGMODEL_API_KEY="your_api_key_here"

Authorization: Bearer YOUR_API_KEY

https://open.bigmodel.cn/api/paas/v4/

POST https://open.bigmodel.cn/api/paas/v4/chat/completions

curl https://open.bigmodel.cn/api/paas/v4/chat/completions \
  -H "Authorization: Bearer $BIGMODEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.1",
    "messages": [
      {
        "role": "user",
        "content": "Write a Python function that finds all prime numbers up to n using the Sieve of Eratosthenes."
      }
    ],
    "max_tokens": 1024,
    "temperature": 0.7
  }'

import os
import requests

api_key = os.environ["BIGMODEL_API_KEY"]

response = requests.post(
    "https://open.bigmodel.cn/api/paas/v4/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    },
    json={
        "model": "glm-5.1",
        "messages": [
            {
                "role": "user",
                "content": "Write a Python function that finds all prime numbers up to n using the Sieve of Eratosthenes."
            }
        ],
        "max_tokens": 1024,
        "temperature": 0.7
    }
)

result = response.json()
print(result["choices"][0]["message"]["content"])

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BIGMODEL_API_KEY"],
    base_url="https://open.bigmodel.cn/api/paas/v4/"
)

response = client.chat.completions.create(
    model="glm-5.1",
    messages=[
        {
            "role": "user",
            "content": "Write a Python function that finds all prime numbers up to n using the Sieve of Eratosthenes."
        }
    ],
    max_tokens=1024,
    temperature=0.7
)

print(response.choices[0].message.content)

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1744000000,
  "model": "glm-5.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "def sieve_of_eratosthenes(n):\n    ..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 32,
    "completion_tokens": 215,
    "total_tokens": 247
  }
}

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BIGMODEL_API_KEY"],
    base_url="https://open.bigmodel.cn/api/paas/v4/"
)

stream = client.chat.completions.create(
    model="glm-5.1",
    messages=[
        {
            "role": "user",
            "content": "Explain how a B-tree index works in a database, with a code example."
        }
    ],
    stream=True,
    max_tokens=2048
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)

print()  # 스트리밍 종료 후 개행

import os
import json
import requests

api_key = os.environ["BIGMODEL_API_KEY"]

response = requests.post(
    "https://open.bigmodel.cn/api/paas/v4/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    },
    json={
        "model": "glm-5.1",
        "messages": [{"role": "user", "content": "Write a merge sort in Python."}],
        "stream": True,
        "max_tokens": 1024
    },
    stream=True
)

for line in response.iter_lines():
    if line:
        line = line.decode("utf-8")
        if line.startswith("data: "):
            data = line[6:]
            if data == "[DONE]":
                break
            chunk = json.loads(data)
            delta = chunk["choices"][0]["delta"]
            if "content" in delta:
                print(delta["content"], end="", flush=True)

import os
import json
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BIGMODEL_API_KEY"],
    base_url="https://open.bigmodel.cn/api/paas/v4/"
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "run_python",
            "description": "Execute Python code and return the output. Use this to test, profile, or benchmark code.",
            "parameters": {
                "type": "object",
                "properties": {
                    "code": {
                        "type": "string",
                        "description": "The Python code to execute"
                    }
                },
                "required": ["code"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "read_file",
            "description": "Read the contents of a file",
            "parameters": {
                "type": "object",
                "properties": {
                    "path": {
                        "type": "string",
                        "description": "File path to read"
                    }
                },
                "required": ["path"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="glm-5.1",
    messages=[
        {
            "role": "user",
            "content": "Write a function to compute Fibonacci numbers, test it for n=10, and show me the output."
        }
    ],
    tools=tools,
    tool_choice="auto"
)

message = response.choices[0].message
print(f"Finish reason: {response.choices[0].finish_reason}")

if message.tool_calls:
    for tool_call in message.tool_calls:
        print(f"\nTool called: {tool_call.function.name}")
        print(f"Arguments: {tool_call.function.arguments}")

import subprocess

def execute_tool(tool_call):
    """도구 실행 후 결과 반환"""
    name = tool_call.function.name
    args = json.loads(tool_call.function.arguments)

    if name == "run_python":
        result = subprocess.run(
            ["python3", "-c", args["code"]],
            capture_output=True,
            text=True,
            timeout=10
        )
        return result.stdout or result.stderr

    elif name == "read_file":
        try:
            with open(args["path"]) as f:
                return f.read()
        except FileNotFoundError:
            return f"Error: file {args['path']} not found"

    return f"Unknown tool: {name}"


def run_agent_loop(user_message, tools, max_iterations=20):
    """도구 호출을 포함한 전체 에이전트 루프 실행"""
    messages = [{"role": "user", "content": user_message}]

    for i in range(max_iterations):
        response = client.chat.completions.create(
            model="glm-5.1",
            messages=messages,
            tools=tools,
            tool_choice="auto",
            max_tokens=4096
        )

        message = response.choices[0].message
        messages.append(message.model_dump())

        if response.choices[0].finish_reason == "stop":
            return message.content

        if response.choices[0].finish_reason == "tool_calls":
            for tool_call in message.tool_calls:
                tool_result = execute_tool(tool_call)
                messages.append({
                    "role": "tool",
                    "tool_call_id": tool_call.id,
                    "content": tool_result
                })

    return "Max iterations reached"


result = run_agent_loop(
    "Write a quicksort implementation, test it with a random list of 1000 integers, and report the time.",
    tools
)
print(result)

{
    "model": "glm-5.1",
    "temperature": 1.0,
    "top_p": 0.95,
    "max_tokens": 163840  # 장기 실행·대용량 컨텍스트
}

{
  "model": "glm-5.1",
  "baseURL": "https://open.bigmodel.cn/api/paas/v4/",
  "apiKey": "your_bigmodel_api_key"
}

{
  "cline.apiProvider": "openai",
  "cline.openAIBaseURL": "https://open.bigmodel.cn/api/paas/v4/",
  "cline.openAIApiKey": "your_bigmodel_api_key",
  "cline.openAIModelId": "glm-5.1"
}

{
  "id": "chatcmpl-test123",
  "object": "chat.completion",
  "created": 1744000000,
  "model": "glm-5.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "def sieve(n): ..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 32,
    "completion_tokens": 120,
    "total_tokens": 152
  }
}

{
  "id": "chatcmpl-tool456",
  "object": "chat.completion",
  "created": 1744000001,
  "model": "glm-5.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_abc",
            "type": "function",
            "function": {
              "name": "run_python",
              "arguments": "{\"code\": \"print(2+2)\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ],
  "usage": {
    "prompt_tokens": 48,
    "completion_tokens": 35,
    "total_tokens": 83
  }
}

{
  "error": {
    "message": "Rate limit exceeded. Please retry after 60 seconds.",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded"
  }
}

import time
import requests

def call_with_retry(payload, max_retries=3):
    for attempt in range(max_retries):
        try:
            response = requests.post(
                "https://open.bigmodel.cn/api/paas/v4/chat/completions",
                headers={"Authorization": f"Bearer {os.environ['BIGMODEL_API_KEY']}",
                         "Content-Type": "application/json"},
                json=payload,
                timeout=120
            )

            if response.status_code == 429:
                retry_after = int(response.headers.get("Retry-After", 60))
                print(f"Rate limited. Waiting {retry_after}s...")
                time.sleep(retry_after)
                continue

            response.raise_for_status()
            return response.json()

        except requests.exceptions.Timeout:
            wait = 2 ** attempt
            print(f"Timeout on attempt {attempt + 1}. Retrying in {wait}s...")
            time.sleep(wait)

    raise Exception("Max retries exceeded")