SeaLink
← Docs

Quickstart

Make your first call in 5 minutes.

1Get an API key

After signing in, go to /dashboard/keys and click "Create new key". The key is shown only once — copy it immediately.

Create free account

2Make your first request

SeaLink speaks both OpenAI and Anthropic protocols. The OpenAI examples below use deepseek-v4-flash, available on all plans. The Anthropic-native endpoint requires Builder plan or above.

cURL (OpenAI)
curl https://api.sealink.asia/v1/chat/completions \
  -H "Authorization: Bearer $SEALINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello, SeaLink."}]
  }'
Python
from openai import OpenAI


client = OpenAI(
    base_url="https://api.sealink.asia/v1",
    api_key="<your-sealink-key>",
)


resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello, SeaLink."}],
)
print(resp.choices[0].message.content)
Node.js
import OpenAI from "openai";


const client = new OpenAI({
  baseURL: "https://api.sealink.asia/v1",
  apiKey: process.env.SEALINK_API_KEY,
});


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


console.log(resp.choices[0].message.content);
cURL (Anthropic)
curl https://api.sealink.asia/anthropic/v1/messages \
  -H "x-api-key: $SEALINK_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello, SeaLink."}]
  }'
Claude Code
export ANTHROPIC_BASE_URL=https://api.sealink.asia/anthropic
export ANTHROPIC_AUTH_TOKEN=$SEALINK_API_KEY


# now run Claude Code as usual
claude

For local development, swap the base URL with http://localhost:3000/api (OpenAI) or http://localhost:3000/api/anthropic (Anthropic).

3That's it

You just made your first successful call. Swap the model ID to use any model supported by your plan.

Next steps