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

# SDK de Python para OpenAI

> Usar el SDK oficial de OpenAI, LangChain y LlamaIndex para integrarse con Crazyrouter

> Contenido actualizado: 2026-06-09

## SDK oficial de OpenAI

```bash theme={null}
pip install openai
```

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

client = OpenAI(
    api_key="sk-xxx",
    base_url="https://api.crazyrouter.com/v1"
)

# 同步调用
response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "你好"}],
    temperature=0.7,
    max_tokens=1000
)
print(response.choices[0].message.content)
```

### Llamada asíncrona

```python theme={null}
from openai import AsyncOpenAI
import asyncio

client = AsyncOpenAI(
    api_key="sk-xxx",
    base_url="https://api.crazyrouter.com/v1"
)

async def main():
    response = await client.chat.completions.create(
        model="gpt-5.5",
        messages=[{"role": "user", "content": "你好"}]
    )
    print(response.choices[0].message.content)

asyncio.run(main())
```

## Integración de LangChain

```bash theme={null}
pip install langchain-openai
```

```python theme={null}
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-5.5",
    api_key="sk-xxx",
    base_url="https://api.crazyrouter.com/v1",
    temperature=0.7
)

# 简单调用
response = llm.invoke("用 Python 写一个快速排序")
print(response.content)
```

### Llamada encadenada con LangChain

```python theme={null}
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(
    model="gpt-5.5",
    api_key="sk-xxx",
    base_url="https://api.crazyrouter.com/v1"
)

prompt = ChatPromptTemplate.from_messages([
    ("system", "你是一个{role}。"),
    ("user", "{input}")
])

chain = prompt | llm
response = chain.invoke({"role": "Python 专家", "input": "解释装饰器"})
print(response.content)
```

### Embeddings de LangChain

```python theme={null}
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-large",
    api_key="sk-xxx",
    base_url="https://api.crazyrouter.com/v1"
)

vectors = embeddings.embed_documents(["文本一", "文本二"])
print(f"向量维度: {len(vectors[0])}")
```

## Integración de LlamaIndex

```bash theme={null}
pip install llama-index-llms-openai llama-index-embeddings-openai
```

```python theme={null}
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding

# LLM 配置
llm = OpenAI(
    model="gpt-5.5",
    api_key="sk-xxx",
    api_base="https://api.crazyrouter.com/v1"
)

response = llm.complete("什么是 RAG？")
print(response.text)

# Embedding 配置
embed_model = OpenAIEmbedding(
    model="text-embedding-3-large",
    api_key="sk-xxx",
    api_base="https://api.crazyrouter.com/v1"
)

vector = embed_model.get_text_embedding("测试文本")
print(f"维度: {len(vector)}")
```

> [!NOTE]
>
> Los ejemplos de chat anteriores usan por defecto `gpt-5.5`, probado exitosamente en entorno productivo el 23 de marzo de 2026. Si necesitas cambiar de modelo, prioritariamente usa `claude-opus-4-8`, ya igualmente validado; para los ejemplos de Embedding sigue usando `text-embedding-3-large`.

## Páginas relacionadas

* [Página del modelo GPT Image 1.5: precio en tiempo real, muestras reales, código de llamada](https://crazyrouter.com/es/models/openai/gpt-image-1-5?utm_source=docs\&utm_medium=related)
* [Página del modelo GPT Image 2: precio en tiempo real, muestras reales, código de llamada](https://crazyrouter.com/es/models/openai/gpt-image-2?utm_source=docs\&utm_medium=related)
* [Todos los modelos y precios de OpenAI](https://crazyrouter.com/es/models/openai?utm_source=docs\&utm_medium=related)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.