SDKs

There's no Thalam-specific SDK because you don't need one. Any client that speaks the OpenAI Chat Completions format works — official SDKs, frameworks, or raw HTTP.

Python

Official openai package:

install

pip install openai

Node / TypeScript

Same package, TypeScript-first:

install

npm install openai
# or: pnpm add openai / bun add openai

client.ts

#60a5fa]">import OpenAI from class="text-emerald-400">"openai";

#60a5fa]">const client = new OpenAI({
  apiKey: process.env.THALAM_KEY,
  baseURL: #60a5fa]">class="text-emerald-400">"https://api.thalam.ai/v1",
});

#60a5fa]">const response = await client.chat.completions.create({
  model: "<model-id>",
  messages: [{ role: #60a5fa]">class="text-emerald-400">"user", content: class="text-emerald-400">"Hello" }],
});

console.log(response.choices[0].message.content);

curl

Raw HTTP works too — no SDK required:

terminal

curl https://api.thalam.ai/v1/chat/completions \
  -H #60a5fa]">class="text-emerald-400">"Content-Type: application/json" \
  -H #60a5fa]">class="text-emerald-400">"Authorization: Bearer tl-xxxxxxxxxxxxxxxxxxxxxxxx" \
  -d '{
    #60a5fa]">class="text-emerald-400">"model": "<model-id>",
    #60a5fa]">class="text-emerald-400">"messages": [{class="text-emerald-400">"role": class="text-emerald-400">"user", class="text-emerald-400">"content": class="text-emerald-400">"Hello"}]
  }'

Frameworks work unchanged. LangChain, LlamaIndex, Instructor, Guidance, Vercel AI SDK — any library that takes an OpenAI client will work once you set the base_url.