GPT-5.6 Luna

GPT-5.6 Luna is the fastest and most economical tier of OpenAI's GPT-5.6 generation, keeping the full 1M-token context window, image input, function calling, and structured outputs. It is built for the high-volume paths where latency and cost per request decide the architecture: chat backends, classification and routing, batch extraction, and retrieval over long context. Use it as the default for scale traffic and escalate to Terra or Sol when a request needs more depth.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-5.6-luna",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)