SDK Quickstart

1. Install

Confirm the local runtime first: TypeScript SDK requires Node.js 18.17+, and Python SDK requires Python 3.10+. After installation, import the Python package as seacloud_sdk.

TypeScript

pnpm add @seacloudai/sdk

Python

pip install seacloudai-sdk

2. Create A Client

The caller must pass the API key explicitly. Your application may read it from an environment variable first, but the SDK does not do that automatically.

TypeScript

import { SeaCloud, getSeaCloudDocs } from "@seacloudai/sdk";

const docs = getSeaCloudDocs();

const client = new SeaCloud({
  apiKey: process.env.SEACLOUD_API_KEY!,
  timeout: 600_000,
});

console.table(docs.methods);

Python

import os

from seacloud_sdk import SeaCloud, getSeaCloudDocs

docs = getSeaCloudDocs()

client = SeaCloud(
    api_key=os.environ["SEACLOUD_API_KEY"],
    timeout=600_000,
)

print(docs["methods"])

3. Send Chat

TypeScript

const text = await client.chat.send(
  "gpt-4.1",
  [{ role: "user", content: "Introduce SeaCloud SDK in one sentence." }],
  { temperature: 0.2, maxTokens: 128 },
);

console.log(text);

Python

text = await client.chat.send(
    "gpt-4.1",
    [{"role": "user", "content": "Introduce SeaCloud SDK in one sentence."}],
    {"temperature": 0.2, "maxTokens": 128},
)

print(text)

4. Run Generation

run creates a task and returns immediately. runSync and run_sync create a task, poll status, read the final response, and return a normalized result.

TypeScript

const result = await client.runSync("wan25_t2i_preview", {
  prompt: "a cinematic photo of a cat astronaut",
  n: 1,
  prompt_extend: true,
  size: "1024*1024",
  watermark: false,
});

console.log(result.output?.urls);

Python

result = await client.run_sync("wan25_t2i_preview", {
    "prompt": "a cinematic photo of a cat astronaut",
    "n": 1,
    "prompt_extend": True,
    "size": "1024*1024",
    "watermark": False,
})

print(result.get("output", {}).get("urls"))

Next

• For dryRun, polling, model specs, and errors, continue to the operation manual.