> ## Documentation Index
> Fetch the complete documentation index at: https://docs.laozhang.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Text Generation (Chat Completions)

> Use large language models for chat completions, supporting single-turn, multi-turn conversations, and role-playing scenarios

## Overview

Text Generation (Chat Completions) is one of the core capabilities of LaoZhang API, supporting 200+ popular AI models for intelligent conversations and text generation. Through a unified OpenAI-compatible interface, you can easily implement:

* **Intelligent Conversations**: Build chatbots and virtual assistants
* **Content Creation**: Article writing, creative generation, copywriting
* **Code Assistance**: Code generation, debugging, refactoring suggestions
* **Knowledge Q\&A**: Answer questions, knowledge retrieval, information extraction
* **Role Playing**: Customized AI characters, scenario simulation

<Info>
  Supports GPT-5, Claude 4, Gemini 2.5, DeepSeek, Qwen and 200+ mainstream models with a single API Key.
</Info>

## Quick Start

### Basic Example

```python theme={null}
from openai import OpenAI

client = OpenAI(
    api_key="sk-your-laozhang-api-key",
    base_url="https://api2.laozhang.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[
        {"role": "user", "content": "Explain the history of artificial intelligence"}
    ]
)

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

### Multi-turn Conversation

```python theme={null}
messages = [
    {"role": "system", "content": "You are a professional Python programming assistant"},
    {"role": "user", "content": "How to read a CSV file?"},
    {"role": "assistant", "content": "You can use pandas library's read_csv() function..."},
    {"role": "user", "content": "How to filter specific column data?"}
]

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=messages
)

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

## Core Parameters

### model (Required)

Specify the model name. See [Model Info](/en/api-capabilities/model-info) for details.

```python theme={null}
model="gpt-5"              # GPT-5 Latest
model="gpt-4.1"            # GPT-4.1 Fast
model="claude-sonnet-4-20250514"  # Claude 4 Sonnet
model="gemini-2.5-pro"     # Gemini 2.5 Pro
model="deepseek-chat"      # DeepSeek Chat
```

### messages (Required)

Array of conversation messages with `role` and `content` fields:

<CardGroup cols={3}>
  <Card title="system" icon="cog">
    System prompt defining AI behavior and role
  </Card>

  <Card title="user" icon="user">
    User message representing user input
  </Card>

  <Card title="assistant" icon="bot">
    Assistant message representing AI response
  </Card>
</CardGroup>

### temperature (Optional)

Controls output randomness, range `0.0 ~ 2.0`, default `1.0`:

| Range          | Characteristics    | Use Cases                        |
| -------------- | ------------------ | -------------------------------- |
| **0.0 \~ 0.3** | More deterministic | Translation, summarization, code |
| **0.7 \~ 1.0** | Balanced           | Daily conversations              |
| **1.0 \~ 2.0** | More creative      | Creative writing, brainstorming  |

### stream (Optional)

Enable streaming output for better user experience:

```python theme={null}
response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Write an article about AI"}],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")
```

## Recommended Models

| Scenario          | Recommended Model                            | Reason             |
| ----------------- | -------------------------------------------- | ------------------ |
| Daily Chat        | `gpt-4.1-mini`, `deepseek-chat`              | Fast, low cost     |
| Complex Reasoning | `gpt-5`, `claude-sonnet-4-20250514`          | Powerful, accurate |
| Code Generation   | `claude-sonnet-4-20250514`, `deepseek-coder` | Excellent coding   |
| Long Text         | `gemini-2.5-pro`, `claude-3-opus`            | Ultra-long context |

## Best Practices

### Optimize Prompts

```python theme={null}
# ❌ Poor prompt
"Write an article"

# ✅ Good prompt
"""Write a popular science article about AI applications in healthcare.

Requirements:
- Length: 800-1000 words
- Audience: General readers
- Structure: Introduction, use cases, case studies, future outlook
- Include 2-3 real examples"""
```

### Error Handling

```python theme={null}
from openai import OpenAI, OpenAIError
import time

def chat_with_retry(messages, max_retries=3):
    for attempt in range(max_retries):
        try:
            response = client.chat.completions.create(
                model="gpt-4.1",
                messages=messages
            )
            return response.choices[0].message.content
        except OpenAIError as e:
            if attempt < max_retries - 1:
                time.sleep(2 ** attempt)
                continue
            raise
```

## Related Documentation

<CardGroup cols={2}>
  <Card title="Model Info" icon="database" href="/en/api-capabilities/model-info">
    View all supported models
  </Card>

  <Card title="Text Embedding" icon="vector-square" href="/en/api-capabilities/text-embedding">
    Convert text to vectors
  </Card>

  <Card title="API Reference" icon="code" href="/en/api-reference/chat-completions">
    Detailed API reference
  </Card>

  <Card title="OpenAI SDK" icon="plug" href="/en/api-capabilities/openai-sdk">
    Quick integration with OpenAI SDK
  </Card>
</CardGroup>