modelslab-chat-generation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

ModelsLab Chat/LLM Generation

ModelsLab 对话/大语言模型生成

Send chat completions to 60+ LLM models through a single OpenAI-compatible endpoint.

通过一个兼容OpenAI的端点，向60余种大语言模型（LLM）发送对话补全请求。

When to Use This Skill

何时使用该功能

Chat with AI models (DeepSeek, Llama, Gemini, Qwen, Mistral)
Build conversational AI applications
Generate text completions with system prompts
Use function/tool calling with LLMs
Stream responses for real-time output
Get structured JSON responses

与AI模型对话（DeepSeek、Llama、Gemini、Qwen、Mistral）
构建对话式AI应用
结合系统提示词生成文本补全内容
为大语言模型（LLM）启用函数/工具调用
流式响应实现实时输出
获取结构化JSON响应

API Endpoint

API端点

Chat Completions:

POST https://modelslab.com/api/v7/llm/chat/completions

The endpoint follows the OpenAI chat completions format, making it easy to switch from OpenAI or use the OpenAI SDK.

Chat Completions:

POST https://modelslab.com/api/v7/llm/chat/completions

该端点遵循OpenAI对话补全格式，方便从OpenAI切换或直接使用OpenAI SDK。

Quick Start

快速开始

python

import requests

def chat(message, api_key, model="meta-llama-3-8B-instruct"):
    """Send a chat completion request.

    Args:
        message: The user message
        api_key: Your ModelsLab API key
        model: LLM model ID (use modelslab models search --feature llmaster to find models)
    """
    response = requests.post(
        "https://modelslab.com/api/v7/llm/chat/completions",
        json={
            "key": api_key,
            "model_id": model,
            "messages": [
                {"role": "user", "content": message}
            ],
            "max_tokens": 200,
            "temperature": 0.7
        }
    )

    data = response.json()

    if "choices" in data:
        return data["choices"][0]["message"]["content"]
    else:
        raise Exception(f"Error: {data.get('message', 'Unknown error')}")

python

import requests

def chat(message, api_key, model="meta-llama-3-8B-instruct"):
    """Send a chat completion request.

    Args:
        message: The user message
        api_key: Your ModelsLab API key
        model: LLM model ID (use modelslab models search --feature llmaster to find models)
    """
    response = requests.post(
        "https://modelslab.com/api/v7/llm/chat/completions",
        json={
            "key": api_key,
            "model_id": model,
            "messages": [
                {"role": "user", "content": message}
            ],
            "max_tokens": 200,
            "temperature": 0.7
        }
    )

    data = response.json()

    if "choices" in data:
        return data["choices"][0]["message"]["content"]
    else:
        raise Exception(f"Error: {data.get('message', 'Unknown error')}")

Usage

reply = chat( "Explain quantum computing in simple terms.", "your_api_key" ) print(reply)

undefined

reply = chat( "Explain quantum computing in simple terms.", "your_api_key" ) print(reply)

undefined

With System Prompt

结合系统提示词

python

def chat_with_system(system_prompt, message, api_key, model="meta-llama-3-8B-instruct"):
    """Chat with a system prompt for role/behavior control."""
    response = requests.post(
        "https://modelslab.com/api/v7/llm/chat/completions",
        json={
            "key": api_key,
            "model_id": model,
            "messages": [
                {"role": "system", "content": system_prompt},
                {"role": "user", "content": message}
            ],
            "max_tokens": 500,
            "temperature": 0.7
        }
    )

    data = response.json()
    if "choices" in data:
        return data["choices"][0]["message"]["content"]

python

def chat_with_system(system_prompt, message, api_key, model="meta-llama-3-8B-instruct"):
    """Chat with a system prompt for role/behavior control."""
    response = requests.post(
        "https://modelslab.com/api/v7/llm/chat/completions",
        json={
            "key": api_key,
            "model_id": model,
            "messages": [
                {"role": "system", "content": system_prompt},
                {"role": "user", "content": message}
            ],
            "max_tokens": 500,
            "temperature": 0.7
        }
    )

    data = response.json()
    if "choices" in data:
        return data["choices"][0]["message"]["content"]

Usage

reply = chat_with_system( "You are a Python expert. Give concise code examples.", "How do I read a CSV file?", "your_api_key" )

undefined

reply = chat_with_system( "You are a Python expert. Give concise code examples.", "How do I read a CSV file?", "your_api_key" )

undefined

Multi-Turn Conversation

多轮对话

python

def conversation(messages, api_key, model="meta-llama-3-8B-instruct"):
    """Send a multi-turn conversation."""
    response = requests.post(
        "https://modelslab.com/api/v7/llm/chat/completions",
        json={
            "key": api_key,
            "model_id": model,
            "messages": messages,
            "max_tokens": 500,
            "temperature": 0.7
        }
    )
    return response.json()

python

def conversation(messages, api_key, model="meta-llama-3-8B-instruct"):
    """Send a multi-turn conversation."""
    response = requests.post(
        "https://modelslab.com/api/v7/llm/chat/completions",
        json={
            "key": api_key,
            "model_id": model,
            "messages": messages,
            "max_tokens": 500,
            "temperature": 0.7
        }
    )
    return response.json()

Multi-turn example

messages = [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is Python?"}, {"role": "assistant", "content": "Python is a high-level programming language..."}, {"role": "user", "content": "Show me a hello world example."} ]

result = conversation(messages, "your_api_key") print(result["choices"][0]["message"]["content"])

undefined

result = conversation(messages, "your_api_key") print(result["choices"][0]["message"]["content"])

undefined

OpenAI SDK Compatibility

兼容OpenAI SDK

You can use the official OpenAI Python SDK by changing the base URL and API key:

python

from openai import OpenAI

client = OpenAI(
    base_url="https://modelslab.com/api/v7/llm",
    api_key="your_modelslab_api_key"
)

response = client.chat.completions.create(
    model="meta-llama-3-8B-instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    max_tokens=100,
    temperature=0.7
)

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

您可以通过修改基础URL和API密钥，使用官方OpenAI Python SDK：

python

from openai import OpenAI

client = OpenAI(
    base_url="https://modelslab.com/api/v7/llm",
    api_key="your_modelslab_api_key"
)

response = client.chat.completions.create(
    model="meta-llama-3-8B-instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    max_tokens=100,
    temperature=0.7
)

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

cURL Example

cURL示例

bash

curl -X POST "https://modelslab.com/api/v7/llm/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "key": "your_api_key",
    "model_id": "meta-llama-3-8B-instruct",
    "messages": [
      {"role": "user", "content": "Say hello in one sentence."}
    ],
    "max_tokens": 50,
    "temperature": 0.7
  }'

bash

curl -X POST "https://modelslab.com/api/v7/llm/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "key": "your_api_key",
    "model_id": "meta-llama-3-8B-instruct",
    "messages": [
      {"role": "user", "content": "Say hello in one sentence."}
    ],
    "max_tokens": 50,
    "temperature": 0.7
  }'

Discovering LLM Models

查找大语言模型（LLM）

bash

undefined

bash

undefined

Search all chat/LLM models

modelslab models search --feature llmaster

Search by provider

modelslab models search --search "deepseek" modelslab models search --search "llama" modelslab models search --search "gemini"

Get model details

modelslab models detail --id meta-llama-3-8B-instruct

undefined

modelslab models detail --id meta-llama-3-8B-instruct

undefined

Popular LLM Model IDs

Key Parameters

关键参数

Parameter	Type	Required	Description
`model_id`	string	Yes	LLM model identifier (alias: `model` )
`messages`	array	Yes	Array of message objects with `role` and `content`
`temperature`	float	No	Sampling temperature (0-2, default varies by model)
`max_tokens`	integer	No	Maximum tokens to generate
`top_p`	float	No	Nucleus sampling (0-1)
`top_k`	integer	No	Top-k sampling
`frequency_penalty`	float	No	Frequency penalty (-2 to 2)
`presence_penalty`	float	No	Presence penalty (-2 to 2)
`streaming`	boolean	No	Enable streaming responses (alias: `stream` )
`n`	integer	No	Number of completions (1-10)
`stop`	array	No	Stop sequences (max 4)
`seed`	integer	No	Random seed for reproducibility
`tools`	array	No	Function/tool definitions
`tool_choice`	string	No	Tool selection strategy
`response_format`	object	No	`{"type": "json_object"}` for JSON mode

参数	类型	是否必填	描述
`model_id`	字符串	是	大语言模型（LLM）标识符（别名： `model` ）
`messages`	数组	是	包含 `role` 和 `content` 的消息对象数组
`temperature`	浮点数	否	采样温度（0-2，默认值因模型而异）
`max_tokens`	整数	否	生成的最大token数
`top_p`	浮点数	否	核采样参数（0-1）
`top_k`	整数	否	Top-k采样参数
`frequency_penalty`	浮点数	否	频率惩罚（-2到2）
`presence_penalty`	浮点数	否	存在惩罚（-2到2）
`streaming`	布尔值	否	启用流式响应（别名： `stream` ）
`n`	整数	否	生成补全结果的数量（1-10）
`stop`	数组	否	停止序列（最多4个）
`seed`	整数	否	用于结果复现的随机种子
`tools`	数组	否	函数/工具定义
`tool_choice`	字符串	否	工具选择策略
`response_format`	对象	否	指定为 `{"type": "json_object"}` 可启用JSON模式

Response Format

响应格式

The response follows the OpenAI chat completions format:

json

{
  "id": "gen-...",
  "model": "meta-llama-3-8B-instruct",
  "object": "chat.completion",
  "created": 1771658583,
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 17,
    "completion_tokens": 10,
    "total_tokens": 27
  }
}

响应遵循OpenAI对话补全格式：

json

{
  "id": "gen-...",
  "model": "meta-llama-3-8B-instruct",
  "object": "chat.completion",
  "created": 1771658583,
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 17,
    "completion_tokens": 10,
    "total_tokens": 27
  }
}

Error Handling

错误处理

python

def safe_chat(message, api_key, model="meta-llama-3-8B-instruct"):
    """Chat with error handling."""
    try:
        response = requests.post(
            "https://modelslab.com/api/v7/llm/chat/completions",
            json={
                "key": api_key,
                "model_id": model,
                "messages": [{"role": "user", "content": message}],
                "max_tokens": 200
            }
        )
        data = response.json()

        if "choices" in data:
            return data["choices"][0]["message"]["content"]
        elif data.get("status") == "error":
            raise Exception(data.get("message", "Unknown error"))
        else:
            raise Exception(f"Unexpected response: {data}")

    except requests.exceptions.RequestException as e:
        raise Exception(f"Network error: {e}")

try:
    reply = safe_chat("Hello!", "your_api_key")
    print(reply)
except Exception as e:
    print(f"Chat failed: {e}")

python

def safe_chat(message, api_key, model="meta-llama-3-8B-instruct"):
    """Chat with error handling."""
    try:
        response = requests.post(
            "https://modelslab.com/api/v7/llm/chat/completions",
            json={
                "key": api_key,
                "model_id": model,
                "messages": [{"role": "user", "content": message}],
                "max_tokens": 200
            }
        )
        data = response.json()

        if "choices" in data:
            return data["choices"][0]["message"]["content"]
        elif data.get("status") == "error":
            raise Exception(data.get("message", "Unknown error"))
        else:
            raise Exception(f"Unexpected response: {data}")

    except requests.exceptions.RequestException as e:
        raise Exception(f"Network error: {e}")

try:
    reply = safe_chat("Hello!", "your_api_key")
    print(reply)
except Exception as e:
    print(f"Chat failed: {e}")

modelslab-chat-generation

Original

Translation

ModelsLab Chat/LLM Generation

ModelsLab 对话/大语言模型生成

When to Use This Skill

何时使用该功能

API Endpoint

API端点

Quick Start

快速开始

Usage

Usage

With System Prompt

结合系统提示词

Usage

Usage

Multi-Turn Conversation

多轮对话

Multi-turn example

Multi-turn example

OpenAI SDK Compatibility

兼容OpenAI SDK

cURL Example

cURL示例

Discovering LLM Models

查找大语言模型（LLM）

Search all chat/LLM models

Search all chat/LLM models

Search by provider

Search by provider

Get model details

Get model details

Popular LLM Model IDs

热门大语言模型（LLM）ID

Meta Llama

Meta Llama

DeepSeek

DeepSeek

Google

Google

Qwen

Qwen

Mistral

Mistral

Key Parameters

关键参数

Response Format

响应格式

Error Handling

错误处理

Resources

相关资源

Related Skills

相关功能