Suanlimao
← Back to all tutorials

Connect your tools

OpenAI and Anthropic SDKs

Call us from your own code with the official SDKs — change only the address and key.

About 8 minFor:Developers calling models from their own code

Before you start

  • Python 3 or Node.js
  • A key stored in an environment variable, not in the code

Step 1 · STEP 0x01

Install and set the key

terminal
$ pip install openai anthropic$ npm install openai @anthropic-ai/sdk$ export API_KEY=<YOUR_API_KEY>
The full key is shown only once, at creation. Missed it? Revoke it and create a new one.

Create a key →

Step 2 · STEP 0x02

OpenAI SDK: Python

python
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.suanlimao.shop/v1", api_key=os.environ["API_KEY"])

resp = client.chat.completions.create(
    model="<MODEL_NAME>",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
terminal
$ python demo.pyHello! How can I help you today?
Use https://api.suanlimao.shop/v1 as the API address (with /v1). If the tool says 404, check whether /v1 is missing or doubled, then read the FAQ below.
Don't guess the model name: open the model plaza, click “Copy model id” on a model card and paste it. A wrong model name is the most common error.

Open the model plaza →

Step 3 · STEP 0x03

OpenAI SDK: Node.js (streaming)

javascript
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.suanlimao.shop/v1", apiKey: process.env.API_KEY });

const stream = await client.chat.completions.create({
  model: "<MODEL_NAME>",
  messages: [{ role: "user", content: "Hello" }],
  stream: true,
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
terminal
$ node demo.mjsHello! How can I help you today?

In streaming mode the last chunk carries usage, followed by data: [DONE]. During long pauses the server sends : ping comment lines to keep the connection open; SDKs ignore them.

Step 4 · STEP 0x04

Anthropic SDK (Claude models)

python
import os
import anthropic

client = anthropic.Anthropic(base_url="https://api.suanlimao.shop", api_key=os.environ["API_KEY"])
msg = client.messages.create(
    model="<MODEL_NAME>",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(msg.content[0].text)
terminal
$ python claude_demo.pyHello! …
The Anthropic SDK's base_url is the root https://api.suanlimao.shop without /v1 — the SDK adds the path. Only the OpenAI SDK takes /v1.

Step 5 · STEP 0x05

No code changes: use environment variables

terminal
$ export OPENAI_BASE_URL=https://api.suanlimao.shop/v1$ export OPENAI_API_KEY=<YOUR_API_KEY>$ python your_existing_script.py
The official OpenAI SDK reads OPENAI_BASE_URL and OPENAI_API_KEY, so existing scripts work without code changes — just use a model name from the plaza.

✓ How to tell it worked

  • The script prints an answer and the Usage page shows the request.

FAQ

404?

OpenAI SDK address takes /v1, the Anthropic SDK does not; then check the model name.

429?

You hit a rate limit or a key budget. Wait for Retry-After and retry with exponential backoff.

Timeouts?

Long outputs and reasoning models take longer — raise the SDK timeout and use streaming to see output sooner.

Related tutorials

Still stuck?

Read the troubleshooting tutorials first. If that does not help, open a ticket with the request_id, time, model and the exact error (never paste your key).