GPT-OSS 120B

GPT-OSS 120B is OpenAI's open-weight 120B-parameter mixture-of-experts model, released for researchers and builders who want OpenAI-lineage quality with open weights. It is tuned for reasoning, coding, and tool use, and supports long context. Use it as a self-hostable-class option, a fine-tuning base, or a cost-efficient frontier-tier model for general production traffic.

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-oss-120b",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

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