SeaLinkSeaLink
/
← Docs

QUICKSTART

Make your first API call in three steps

Create a key, change the base URL, and send one OpenAI-compatible request.

Base URL
https://test.sealink.io/v1
Auth
Bearer $SEALINK_API_KEY
Starter model
gpt-4o-mini
01

Create an API Key

Sign in to SeaLink, then create an API Key from your dashboard. The full key string is only shown once upon creation — afterwards, SeaLink only displays the prefix. We recommend copying it right away. If you lose a key, you can always rotate it from the dashboard to generate a new one.

02

Change the base URL and call

For OpenAI SDKs and most tools, you only need to change the base_url and api_key. We recommend sending one real request with your target model to verify before going live.

cURL · OpenAI
curl --request POST \
https://test.sealink.io/v1/chat/completions \
-H "Authorization: Bearer $SEALINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o-mini",
"messages": [
{ "role": "user", "content": "Hello, SeaLink." }
]
}'
SDK / Claude Code examples
Python · OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://test.sealink.io/v1",
api_key="<your-sealink-key>",
)
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hello, SeaLink."}],
)
print(response.choices[0].message.content)
Claude Code
export ANTHROPIC_BASE_URL=https://test.sealink.io/anthropic
export ANTHROPIC_API_KEY=$SEALINK_API_KEY
claude
03

Check the result

  • A 'choices' field in the response means the model returned content successfully.
  • A 'usage' field means token accounting was recorded for this request.
  • If the request fails, check your API key, balance, model ID spelling, and that the base URL ends with /v1.