SDK Setup

DevLens implements the OpenAI API specification. Any SDK or tool that supports custom baseURL works out of the box.

Configuration

Two parameters. That's it.

Parameter	Value
API Key	sk-YOUR_KEY (generate in Console)
Base URL	https://api.devlens.top/v1

Python

pip install openai

from openai import OpenAI

client = OpenAI(
    api_key="sk-YOUR_KEY",
    base_url="https://api.devlens.top/v1"
)

response = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello"}],
    temperature=0.7,
    max_tokens=4096
)
print(response.choices[0].message.content)

Streaming:

stream = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Explain quicksort"}],
    stream=True
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

Node.js / TypeScript

npm install openai

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-YOUR_KEY',
  baseURL: 'https://api.devlens.top/v1',
});

const response = await client.chat.completions.create({
  model: 'gpt-5',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(response.choices[0].message.content);

Streaming:

const stream = await client.chat.completions.create({
  model: 'gpt-5',
  messages: [{ role: 'user', content: 'Explain quicksort' }],
  stream: true,
});

for await (const chunk of stream) {
  const delta = chunk.choices?.[0]?.delta?.content;
  if (delta) process.stdout.write(delta);
}

Environment variables

Recommended approach — no hardcoded secrets:

export OPENAI_API_KEY=sk-YOUR_KEY
export OPENAI_BASE_URL=https://api.devlens.top/v1

client = OpenAI()  # reads OPENAI_API_KEY and OPENAI_BASE_URL automatically

Compatible tools

Any tool that accepts a custom OpenAI base URL works with DevLens:

Tool	Configuration
LangChain	openai_api_base parameter
LlamaIndex	api_base parameter
Cursor	Settings → Models → OpenAI API Base
Continue.dev	apiBase in config.json
ChatBox	Settings → API Host