LS Coder

Built for software engineering

codingagents

LS Coder is tuned for real engineering work: writing and refactoring code, debugging stack traces, generating tests, explaining unfamiliar codebases and working through architecture. It produces complete files instead of fragments and follows instructions precisely.

Call LS Coder from code

Use the model slug ls-coder with any OpenAI-compatible client.

curl

bash
curl https://lessstrict.com/v1/chat/completions \
  -H "Authorization: Bearer $LESSSTRICT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ls-coder",
    "messages": [{"role": "user", "content": "Explain what a mutex is in two sentences."}],
    "stream": true
  }'

Python

python
from openai import OpenAI

client = OpenAI(base_url="https://lessstrict.com/v1", api_key="lsk_...")

stream = client.chat.completions.create(
    model="ls-coder",
    messages=[{"role": "user", "content": "Explain what a mutex is in two sentences."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Node.js

ts
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://lessstrict.com/v1", apiKey: process.env.LESSSTRICT_API_KEY });

const stream = await client.chat.completions.create({
  model: "ls-coder",
  messages: [{ role: "user", content: "Explain what a mutex is in two sentences." }],
  stream: true,
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");

Full reference in the API docs.