OpenAI SDK Integration

CloudBase AI is compatible with both OpenAI Chat Completions and Anthropic Messages API protocols. You can use the OpenAI SDK directly, making it easy to migrate existing projects or switch between models.

Online Example

Open full example code in CodeSandbox →

Prerequisites

1. A CloudBase environment (older plans can be upgraded), with model switch enabled (see Overview)
2. An API Key is created (Get one here)

Installation

# Node.js
npm install openai

# Python
pip install openai

Configuration

Replace the OpenAI SDK's baseURL and apiKey with your CloudBase settings:

Field	Value
baseURL	https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/<PROVIDER>
apiKey	Your CloudBase API Key

Supported Providers

Provider	Description
cloudbase	Resource-Point Plan (unified entry, supports multiple models)

Node.js Examples

Non-streaming

const OpenAI = require("openai");

const client = new OpenAI({
  apiKey: "<YOUR_API_KEY>",
  baseURL: "https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase"
});

async function main() {
  const completion = await client.chat.completions.create({
    model: "deepseek-v4-flash",
    messages: [{ role: "user", content: "Hello" }],
    temperature: 0.7
  });

  console.log(completion.choices[0].message.content);
}

main();

Streaming

const OpenAI = require("openai");

const client = new OpenAI({
  apiKey: "<YOUR_API_KEY>",
  baseURL: "https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase"
});

async function main() {
  const stream = await client.chat.completions.create({
    model: "deepseek-v4-flash",
    messages: [{ role: "user", content: "Introduce yourself" }],
    stream: true
  });

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

main();

Python Examples

Non-streaming

from openai import OpenAI

client = OpenAI(
    api_key="<YOUR_API_KEY>",
    base_url="https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase"
)

completion = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello"}],
    temperature=0.7
)

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

Streaming

from openai import OpenAI

client = OpenAI(
    api_key="<YOUR_API_KEY>",
    base_url="https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase"
)

stream = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Introduce yourself"}],
    stream=True
)

for chunk in stream:
    content = chunk.choices[0].delta.content or ""
    print(content, end="", flush=True)

Multi-turn Conversations

Multi-turn conversations require maintaining a complete messages array in each request. See the Multi-turn Conversation documentation for details.

Switching Models

Simply modify the provider in baseURL and the model parameter to switch between different models:

// Using cloudbase (Resource-Point Plan, recommended)
const cloudbaseClient = new OpenAI({
  apiKey: "<YOUR_API_KEY>",
  baseURL: "https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase"
});

await cloudbaseClient.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Hello" }]
});

Supported Parameters

Parameter	Type	Description
model	string	Model name
messages	array	List of messages
stream	boolean	Enable streaming
temperature	number	Sampling temperature (0-2)
top_p	number	Nucleus sampling (0-1)
max_tokens	number	Maximum tokens to generate
presence_penalty	number	Presence penalty
frequency_penalty	number	Frequency penalty

Migrating from OpenAI

If your project already uses OpenAI, migrating to CloudBase only takes two steps:

1. Update the configuration

// Original OpenAI configuration
const client = new OpenAI({
  apiKey: "sk-xxx"  // OpenAI API Key
});

// CloudBase configuration
const client = new OpenAI({
  apiKey: "<YOUR_CLOUDBASE_API_KEY>",
  baseURL: "https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase"
});

2. Update the model name

// Original OpenAI model
model: "gpt-4"

// CloudBase-supported model
model: "deepseek-v4-flash"  // or any other enabled model

Related Documentation

If you use the Anthropic SDK, you can connect to CloudBase in the same way. See Anthropic SDK Integration.

Error Handling

const OpenAI = require("openai");

const client = new OpenAI({
  apiKey: "<YOUR_API_KEY>",
  baseURL: "https://<ENV_ID>.api.tcloudbasegateway.com/v1/ai/cloudbase"
});

try {
  const completion = await client.chat.completions.create({
    model: "deepseek-v4-flash",
    messages: [{ role: "user", content: "Hello" }]
  });
  console.log(completion.choices[0].message.content);
} catch (error) {
  if (error instanceof OpenAI.APIError) {
    console.error("API Error:", error.status, error.message);
  } else {
    throw error;
  }
}