LS Thinker

Deep reasoning for hard problems

reasoningresearchcoding

LS Thinker reasons step by step before answering. Use it for math, logic puzzles, complex planning, data analysis and anything where a careful chain of thought beats a fast reply. It shows its reasoning when available.

Call LS Thinker from code

Use the model slug ls-thinker 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-thinker",
    "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-thinker",
    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-thinker",
  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.