Docs / Quickstart
This quickstart keeps only paths that can be verified immediately: create an API key, set an environment variable, and make a curl request. DeepAILab SDKs are not shown as the primary path until they are publicly available.
Create a key from the API Keys page. Store it in local environment variables or server-side secret management, never in client-side code.
Set the key in your shell or deployment environment.
export DEEPAILAB_API_KEY="your-api-key-here"DeepAILab API follows an OpenAI-compatible shape. Start with curl to verify network, key, model id, and quota.
curl https://api.deepailab.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $DEEPAILAB_API_KEY" \
-d '{
"model": "claude-sonnet-4-6",
"messages": [
{"role": "user", "content": "Explain DeepAILab API in one sentence"}
]
}'If you use Claude Code, OpenClaw, OpenCode, or DAL Code, start from /dev-tools and follow Detect, Preview, Install, Verify, Rollback.
We recommend REST/curl or OpenAI-compatible clients for fast integration with the DeepAILab API.
Use the official openai npm package with baseURL.
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.DEEPAILAB_API_KEY,
baseURL: "https://api.deepailab.ai/v1",
});
const response = await client.chat.completions.create({
model: "claude-sonnet-4-6",
messages: [{ role: "user", content: "Hello DeepAILab" }],
});
console.log(response.choices[0]?.message?.content);Use the official openai Python package with base_url.
from openai import OpenAI
import os
client = OpenAI(
api_key=os.environ["DEEPAILAB_API_KEY"],
base_url="https://api.deepailab.ai/v1",
)
response = client.chat.completions.create(
model="claude-sonnet-4-6",
messages=[{"role": "user", "content": "Hello DeepAILab"}],
)
print(response.choices[0].message.content)