openai-api

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

OpenAI API

Package: openai@6.9.1 | Last Updated: 2025-11-21

包：openai@6.9.1 | 最后更新时间：2025-11-21

Quick Start

快速开始

bash

bun add openai
export OPENAI_API_KEY="sk-..."

typescript

import OpenAI from 'openai';

const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }]
});

bash

bun add openai
export OPENAI_API_KEY="sk-..."

typescript

import OpenAI from 'openai';

const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }]
});

Current Models (2025)

当前可用模型（2025年）

gpt-5.2: Most capable (128k context)
gpt-4o: Fast multimodal (128k context)
gpt-4o-mini: Cost-effective (128k context)
gpt-4o-transcribe: Audio transcription optimized
gpt-4o-mini-transcribe: Cost-effective transcription
o1-preview: Advanced reasoning (128k context)
o1-mini: Fast reasoning (128k context)

gpt-5.2：功能最强大（128k上下文）
gpt-4o：快速多模态模型（128k上下文）
gpt-4o-mini：高性价比（128k上下文）
gpt-4o-transcribe：音频转录优化模型
gpt-4o-mini-transcribe：高性价比转录模型
o1-preview：高级推理模型（128k上下文）
o1-mini：快速推理模型（128k上下文）

Chat Completions

聊天补全

typescript

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant' },
    { role: 'user', content: 'Explain AI' }
  ],
  temperature: 0.7,
  max_tokens: 1000
});

typescript

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant' },
    { role: 'user', content: 'Explain AI' }
  ],
  temperature: 0.7,
  max_tokens: 1000
});

Streaming

流式响应

typescript

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Tell a story' }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

typescript

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Tell a story' }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Function Calling

函数调用

typescript

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'What is the weather?' }],
  tools: [{
    type: 'function',
    function: {
      name: 'getWeather',
      parameters: {
        type: 'object',
        properties: { location: { type: 'string' } },
        required: ['location']
      }
    }
  }]
});

typescript

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'What is the weather?' }],
  tools: [{
    type: 'function',
    function: {
      name: 'getWeather',
      parameters: {
        type: 'object',
        properties: { location: { type: 'string' } },
        required: ['location']
      }
    }
  }]
});

Embeddings

嵌入

typescript

const response = await client.embeddings.create({
  model: 'text-embedding-3-small',
  input: 'Your text here'
});

const embedding = response.data[0].embedding; // 1536 dimensions

typescript

const response = await client.embeddings.create({
  model: 'text-embedding-3-small',
  input: 'Your text here'
});

const embedding = response.data[0].embedding; // 1536 dimensions

Images (GPT-Image-1.5)

图像生成（GPT-Image-1.5）

typescript

const image = await client.images.generate({
  model: 'gpt-image-1.5',
  prompt: 'A serene landscape',
  size: '1024x1024',
  quality: 'standard'  // or 'hd'
});

typescript

const image = await client.images.generate({
  model: 'gpt-image-1.5',
  prompt: 'A serene landscape',
  size: '1024x1024',
  quality: 'standard'  // or 'hd'
});

Audio

音频处理

Transcription (Whisper):

typescript

const transcription = await client.audio.transcriptions.create({
  file: fs.createReadStream('audio.mp3'),
  model: 'whisper-1'
});

Text-to-Speech:

typescript

const speech = await client.audio.speech.create({
  model: 'tts-1',
  voice: 'alloy',
  input: 'Hello world'
});

转录（Whisper）:

typescript

const transcription = await client.audio.transcriptions.create({
  file: fs.createReadStream('audio.mp3'),
  model: 'whisper-1'
});

文本转语音:

typescript

const speech = await client.audio.speech.create({
  model: 'tts-1',
  voice: 'alloy',
  input: 'Hello world'
});

Top Errors

常见错误

Invalid API Key (401): Verify OPENAI_API_KEY
Rate Limit (429): Implement exponential backoff
Model Not Found (404): Use correct model names
Context Length (400): Reduce input size
Invalid JSON: Fix function calling schemas

See:

references/error-catalog.md

无效API密钥（401）：验证OPENAI_API_KEY是否正确
请求频率限制（429）：实现指数退避策略
模型未找到（404）：使用正确的模型名称
上下文长度超限（400）：缩小输入内容的规模
JSON格式无效：修复函数调用的Schema

参考文档：

references/error-catalog.md

Resources

资源

Reference Guides

参考指南

```
references/models-guide.md
```
- Complete model comparison and selection
```
references/function-calling-patterns.md
```
- Function calling best practices
```
references/structured-output-guide.md
```
- Structured outputs with JSON Schema
```
references/embeddings-guide.md
```
- Text embeddings and vector search
```
references/images-guide.md
```
- GPT-Image-1.5 image generation
```
references/audio-guide.md
```
- Whisper transcription + TTS
```
references/cost-optimization.md
```
- Token optimization and pricing
```
references/top-errors.md
```
- Top 20 errors with solutions
```
references/error-catalog.md
```
- Complete error reference

```
references/models-guide.md
```
- 完整的模型对比与选择指南
```
references/function-calling-patterns.md
```
- 函数调用最佳实践
```
references/structured-output-guide.md
```
- 基于JSON Schema的结构化输出
```
references/embeddings-guide.md
```
- 文本嵌入与向量搜索
```
references/images-guide.md
```
- GPT-Image-1.5图像生成指南
```
references/audio-guide.md
```
- Whisper转录 + TTS指南
```
references/cost-optimization.md
```
- Token优化与定价指南
```
references/top-errors.md
```
- 20种常见错误及解决方案
```
references/error-catalog.md
```
- 完整错误参考手册

Templates

模板

```
templates/basic-usage.ts
```
- Quick start example
```
templates/chat-completion-basic.ts
```
- Basic chat completion
```
templates/chat-completion-nodejs.ts
```
- Node.js implementation
```
templates/streaming-chat.ts
```
- Streaming responses
```
templates/streaming-fetch.ts
```
- Streaming with fetch API
```
templates/function-calling.ts
```
- Tools and function calling
```
templates/structured-output.ts
```
- JSON Schema outputs
```
templates/vision-gpt4o.ts
```
- Vision with GPT-4o
```
templates/embeddings.ts
```
- Text embeddings
```
templates/image-generation.ts
```
- GPT-Image-1.5 generation
```
templates/image-editing.ts
```
- Image editing
```
templates/audio-transcription.ts
```
- Whisper transcription
```
templates/text-to-speech.ts
```
- TTS with voices
```
templates/moderation.ts
```
- Content moderation
```
templates/rate-limit-handling.ts
```
- Exponential backoff
```
templates/cloudflare-worker.ts
```
- Cloudflare Workers integration

Docs: https://platform.openai.com/docs

```
templates/basic-usage.ts
```
- 快速入门示例
```
templates/chat-completion-basic.ts
```
- 基础聊天补全示例
```
templates/chat-completion-nodejs.ts
```
- Node.js实现示例
```
templates/streaming-chat.ts
```
- 流式响应示例
```
templates/streaming-fetch.ts
```
- 使用fetch API实现流式响应
```
templates/function-calling.ts
```
- 工具与函数调用示例
```
templates/structured-output.ts
```
- JSON Schema输出示例
```
templates/vision-gpt4o.ts
```
- GPT-4o视觉功能示例
```
templates/embeddings.ts
```
- 文本嵌入示例
```
templates/image-generation.ts
```
- GPT-Image-1.5图像生成示例
```
templates/image-editing.ts
```
- 图像编辑示例
```
templates/audio-transcription.ts
```
- Whisper转录示例
```
templates/text-to-speech.ts
```
- 带语音选择的TTS示例
```
templates/moderation.ts
```
- 内容审核示例
```
templates/rate-limit-handling.ts
```
- 指数退避实现示例
```
templates/cloudflare-worker.ts
```
- Cloudflare Workers集成示例

官方文档：https://platform.openai.com/docs